ISCA - International Speech
Communication Association


ISCApad Archive  »  2014  »  ISCApad #190  »  Jobs

ISCApad #190

Thursday, April 10, 2014 by Chris Wellekens

6 Jobs
6-1(2013-11-04) Ingénieur de Recherche en Linguistique empirique au LABEX Empirical Foundations of Linguistics

Le LABEX Empirical Foundations of Linguistics cherche un        Ingénieur de Recherche en Linguistique empirique

  

 

  

CONTACT: 

  

Barbara Hemforth, LLF

  

ADRESSE        DU RESPONSABLE: 

  

barbara.hemforth_ at_univ-paris-diderot.fr

  

UNIVERSITÉ: 

  

Université  Paris 7

  

NIVEAU: 

  

ingénieur

  

DURÉE: 

  

23  mois (1er février 2014-31 décembre 2015), renouvelable     

  

SALAIRE: 

  

Entre  1600 et 2000 € par mois (net) en fonction de la  qualification

  

SPÉCIALITÉS: 

  

Linguistique  empirique, Psycholinguistique, Mouvement oculaire,  EEG, Techniques      comportementales

  

DATE  LIMITE DE CANDIDATURE:

 

15/12/2014

 

ADRESSE POUR LA CANDIDATURE: 

 

barbara.hemforth_at_univ-paris-diderot.fr

 

RÉFÉRENCE  DE CANDIDATURE: 

 

EFL-EM3/4

 

Description

 

Les candidats sont appelés à travailler dans le cadre d'un projet en linguistique sur 10 ans intitulé 'Empirical foundations of  linguistics' C'est un  travail à temps plein. Il est possible d'envisager deux ingénieurs à temps  partiel en fonction des candidatures.

 

Le  candidat retenu devra présenter ses diplômes en  linguistique et psycholinguistique du niveau Master. Un doctorat sera  un atout supplémentaire. Le français pourra s'avérer utile mais pas nécessaire. Les candidats seront   auditionnés par un comité d'experts. L'accent sera  mis sur les qualités du candidat pour la recherche empirique (bonnes      connaissances de paradigmes expérimentaux et statistiques), attestées par un     mémoire de Master ou  équivalent, ou une thèse de doctorat (ou PhD) ou d'autres travaux de recherche. Joindre à la candidature :

  

•  un CV

  

•  deux noms de référents (avec leur adresse  email)

  

•  Adresse email et publications

  

Le  candidat travaillera avec une équipe interdisciplinaire composée de linguistes,      de psycholinguistes et de linguistes informaticiens. L'activité consistera :

  • à harmoniser et mutualiser les techniques expérimentales du Labex

  • à  développer de nouveaux paradigmes (surtout mouvements  oculaires et EEG).

  • Le   candidat participera à la coordination du travail  empirique et à l'enseignement.

  • Nous recherchons un candidat ayant une formation solide en linguistique et psycholinguistique et de hautes aptitudes techniques et  sociales.

 

Top

6-2(2013-11-15) Post-doc in the project CHASING, Radbout University, The Netherlands

Vacancy for a post-doc in the project CHASING :
CHAllenging Speech training In Neurological patients by interactive Gaming

see http://hstrik.ruhosting.nl/chasing/
and http://hstrik.ruhosting.nl/chasing-post-doc-vacancy/

* Requirements
- you have a PhD in Computational or Applied Linguistics, Computer Science, Artificial Intelligence, Informatics, Cognitive Science, or Education;
- you are an experienced experimental researcher;
- you have a demonstrable ability to work in a team;
- you have programming skills- (e.g. Python, Java, JavaScript, HTML5, C/C++);
- you have an interest in e-Health, especially gaming and speech technology for speech training;
- you have a good command of the English language. Knowledge of Dutch is considered an advantage;
- you have good communication skills.

* Job description
As a postdoctoral researcher you will take part in the research project CHASING: 'CHAllenging Speech training In Neurological patients through Interactive Gaming'.
Current results indicate the need to develop advanced, motivating training devices that provide guidance on articulation improvement and support the integrated benefits of intensified, independent speech training. Since serious games are known to have strong motivational power, the CHASING project aims to investigate to what extent serious games and game principles motivate and support neurological patients in speech training.
To this end, an interactive, intuitive, user adaptive game for speech training which employs advanced speech technology will be developed and tested.
Your work will mainly address research question 1: How can speech technology and gaming be combined in an advanced, robust application for speech therapy that provides the necessary feedback?
You will be involved in developing dedicated speech technology, especially 'automatic speech recognition' (ASR) technology, integrating it into the game and in designing the game. You will carry out experiments with neurological patients, to study the effects of the game and how the game (incl. the speech technology) can be improved.

* Contact persons
  + Helmer Strik
    w.strik@let.ru.nl
    +31 24 3616104
  + Lilian Beijer
    L.beijer@maartenskliniek.nl
    +31 24 3659718 / 3659140

Top

6-3(2013-11-15) Director at ICSI, Berkeley, CA, USA

DIRECTOR SEARCH

International Computer Science Institute

Berkeley, California

The International Computer Science Institute (ICSI) is a leading center for research in computer

science and one of the few independent, nonprofit research institutes in the United States. With its

unique emphasis on international collaboration, ICSI brings together experts from around the world to

focus on a variety of computer science topics. This is accomplished through active international

visitor programs in which researchers from abroad visit ICSI to work with staff scientists and their

networks of academic, government, and industrial partners. There are approximately eighty scientists

in residence at ICSI including principal investigators, postdoctoral associates, visiting researchers, and

students. ICSI funding primarily comes from US Federal agencies and international visitor programs.

To learn more about ICSI, please go to

http://www.icsi.berkely.edu

ICSI is currently seeking candidates for Director of the institute. The Director will serve as the leader

and administrative head of the Institute, and report directly to the Board of Trustees. As institute

leader, the ICSI Director’s primary responsibilities are to act as an external advocate for ICSI research

and to work collaboratively with ICSI researchers and staff to: strengthen and expand ICSI’s research

agenda, identify and pursue strategic funding opportunities; maintain and expand ICSI’s international

visitor programs; and re-envision ICSI’s relationship with UC Berkeley. The Director will also

continue her/his own research program, if applicable, but the Director’s main goal is to create an

environment that enables ICSI researchers to succeed.

ICSI is an Affirmative Action/Equal Opportunity Employer. Applications from women and minorities

are especially encouraged. Please send CVs to

apply-director@ICSI.Berkeley.EDU

.

Top

6-4(2013-12-12) TWO SPEECH TECHNOLOGY RESEARCHERS, NIICT, Kyoto, Japan

*** JOB OPENINGS FOR TWO SPEECH TECHNOLOGY RESEARCHERS ***

Research Positions in Spoken Language Communication Technology  at Spoken Language Communication Laboratory National Institute of Information and Communications Technology, Kyoto, Japan http://www.nict.go.jp/en/general_affairs/employment/index-e-top2013-9.html http://www2.nict.go.jp/general_affairs/personnel/tempstaffinfo/exr-e/H26/2014R-9.pdf

Applications are invited for the above full-time research positions in the areas of ASR, TTS and Spoken Dialogue, with planned starting date of 1st April 2014. The closing date for applications is 29th November 2013, but we are going to extend it until the positions are filled.

The National Institute of Information and Communications Technology (NICT) is Japan's administrative research institution specializing in the field of information and communications technology, and the NICT Spoken Language Communication Laboratory, based in Kyoto, is a world-leading group in the field of innovative speech technology research. Informal inquiries should be made to Dr Yoshi Shiga (yoshi.shiga@nict.go.jp).

Top

6-5(2014-01-16) POST-DOCTORAL POSITION FOR THE PROJECT TYPALOC (LPL - AIX-EN-PROVENCE, FRANCE)

POST-DOCTORAL POSITION FOR THE PROJECT TYPALOC (LPL - AIX-EN-PROVENCE, FRANCE)

We invite applications for a one-year Post‐Doctoral position at the Laboratoire Parole et Langage (LPL, Aix-Marseille Université, CNRS, UMR 7309, France), to work on the project TYPALOC (Normal and Abnormal Speech Variations: TYPology, Adaptation, LOCalisation).

•    Description
The TYPALOC project is funded by the The French National Research Agency (ANR). It aims at understanding the mechanisms of speech variation, which may be the result of physiological and/or linguistic constraints. In order to achieve this, the productions of healthy speakers and speakers suffering from dysarthria are compared. The production of these two populations is observed through different speech styles (reading and spontaneous speech) to highlight the mechanisms of speaker adaptation. The corpora are manually or automatically annotated at different levels (phonetic, syllabic, lexical, prosodic, etc.). Large-scale data processing and statistical analyses are therefore necessary to achieve the project.
More information is available at the project website:
http://typaloc.univ-avignon.fr/index.html


•    Job description
The post‐doctoral fellow will be mainly involved in data processing. He/she will participate in the acoustic analyses and will then have to implement the statistical analyses planned in the project.

•    Qualifications
A Ph.D. in linguistics or experimental phonetics and solid competence/experience in statistics and data analysis are required. Experience in speech-language pathology or speech therapy is also welcome.

•    Application procedure
Candidates should send a detailed CV with a list of publications, and a cover letter with statement of research interests and details of their experience in data analysis.
Please e-mail documents to:
christine.meunier@lpl-aix.fr
(Christine Meunier, LPL, Aix-en-Provence, France).

Deadline for submission: March 1, 2014
Expected start date: May 2014 (There is some flexibility.)
Length of contract: 12 months
Salary: €2000/month (net)

   

Top

6-6(2014-01-20) Professeur des universités (PR0002) à l'Université Sorbonne Nouvelle Paris 3

Un poste de Professeur des universités (PR0002) est ouvert au recrutement pour la rentrée 2014 à l'Université Sorbonne Nouvelle Paris 3. Voici le descriptif ci-dessous.

 

Enseignement :

 

L’enseignant(e) recruté(e) pour ce poste interviendra à tous les niveaux de formation (licence, master, doctorat), et devra se consacrer à la formation en sciences phonétiques : phonétique acoustique et articulatoire, aspects perceptifs/cognitifs et communicationnels de la parole, didactique de la phonétique, prosodie, phonétique comparée des langues, phonétique clinique, phonologie , phonologie de laboratoire, etc. (cf. http://www.ilpga.univ-paris3.fr/documents/descriptifs-licence.pdf) et de Master  (http://www.ilpga.univ-paris3.fr/brochures/Brochure-LLP.pdf) de Sciences du Langage.

 

Composante / UFR / Lieu(x) d’exercice :

Université Sorbonne Nouvelle Paris 3

Institut de Linguistique et Phonétique Générales Appliquées

19, rue des Bernardins, 75005 Paris.

 


Recherche :

 

Le/la candidat(e) inscrira ses recherches au sein du Laboratoire de Phonétique et Phonologie (LPP, Unité Mixte de Recherche 7018), dont l’objectif est de favoriser l’enrichissement mutuel entre les sciences phonétiques et la phonologie, et l’application de cette synergie dans un grand nombre de domaines, tels que l’apprentissage d’une langue nouvelle, l’acquisition du langage, la remédiation, la typologie des langues, etc.

 

Les thèmes de recherche du laboratoire pour les cinq prochaines années sont les suivants : Phonétique et phonologie des langues du monde, Phonétique clinique, Développement d’instrumentations, Questionnements phonétiques, phonologiques et psycholinguistiques, TAL et Phonétique / phonologie de corpus, Acquisition d’une langue étrangère.

 

Le laboratoire de phonétique et de phonologie est membre fondateur du labex « Empirical Foundations of Linguistics » (EFL : http://www.labex-efl.org/), et les travaux de recherche du candidat devront également s’inscrire dans ses thématiques.

 

 

 

Laboratoire de rattachement : Laboratoire de Phonétique et Phonologie (LPP), UMR 7018 (http://lpp.in2p3.fr/)

 

Administration :

 

Le/la candidat(e) assumera des responsabilités administratives, pédagogiques et scientifiques au sein du laboratoire et du département. Il/elle travaillera activement au maintien et au développement des contacts avec le secteur de la santé, de l'orthophonie et de l'éducation., ainsi qu’aux synergies internes à Sorbonne Paris Cité.'

 

 

Pour plus d'informations :

 

Contacts : Jacqueline Vaissière; Pierre Hallé
Téléphone : 01 44 32 05 74
E-mail : vaissiere238@gmail.com, pierre.halle@univ-paris3.fr

Top

6-7(2014-01-19) Poste de Maitre de Conférences (MCF0621) à l'Université Sorbonne Nouvelle Paris 3.

 

 

Un poste de Maitre de Conférences (MCF0621) est ouvert au recrutement pour la rentrée 2014 à l'Université Sorbonne Nouvelle Paris 3. Voici le descriptif ci-dessous.

 

Enseignement :

 

L’enseignant(e) recruté(e) pour ce poste interviendra en licence et en master des sciences du langage (cf. pour la licence : http://www.ilpga.univ-paris3.fr/documents/descriptifs-licence.pdf et pour le master  http://www.ilpga.univ-paris3.fr/masters.html).  Il/elle assurera des enseignements fondamentaux en linguistique générale et dans son domaine de spécialité (phonologie, morphologie, etc.). Il/elle renforcera les connaissances générales sur la diversité des langues auprès du public étudiant de l’ILPGA, dont c’est une spécificité

 

Composante / UFR / Lieu(x) d’exercice :

Université Sorbonne Nouvelle Paris 3

Institut de Linguistique et Phonétique Générales Appliquées

19, rue des Bernardins, 75005 Paris.

 


Recherche :

 

            Le/la candidat(e) inscrira ses recherches dans une des unités de recherche liées à l’ILPGA, en particulier le Laboratoire de Phonétique et de Phonologie et le Lacito, avec les thématiques desquelles ses travaux devront être convergents. Il/elle développera des recherches dans les domaines de la phonologie, de la morphologie et/ou de la syntaxe, dans une perspective de diversité des langues (expertise d’une famille ou d’une aire linguistique, ou approche typologique). Seront par ailleurs privilégiés les approches et les modèles fondés sur des contraintes.

 

 

Laboratoire de rattachement : Laboratoire de Phonétique et Phonologie (LPP), UMR 7018 (http://lpp.in2p3.fr/) ou LACITO (Laboratoire des Langues et Civilisations à Tradition Orale), UMR7107 (http://lacito.vjf.cnrs.fr/).


Autres :

Le/la candidat(e) assumera des responsabilités administratives, pédagogiques et scientifiques au sein du département.

 

Pour plus d'informations :

 

Contacts : Cédric Gendrot

Téléphone : 01 44 32 05 74

E-mail : cgendrot@univ-paris3.fr

Top

6-8(2014-01-21) Postdoctoral fellowship opportunities for finish German PhD students at ICSI in Berkeley

Postdoctoral fellowship opportunities for finish German PhD students at ICSI in Berkeley 

for details :

https://www.daad.de/ausland/studieren/stipendium/de/19047-internationale-forschungsaufenthalte-in-der-informationstechnologie-fitweltweit/

Top

6-9(2014-01-22) POSTDOCTORAL POSITION at PAROLE team, Inria Nancy, France

POSTDOCTORAL POSITION

*SUBJECT*: Deep neural networks for source separation and noise-robust ASR

*LAB*: PAROLE team, Inria Nancy, France
*SUPERVISORS*: Antoine Liutkus (antoine.liutkus@inria.fr) and Emmanuel Vincent (emmanuel.vincent@inria.fr)
*START*: between November 2014 and January 2015
*DURATION*: 12 to 16 months
*TO APPLY*: apply online before June 10 at http://www.inria.fr/en/institute/recruitment/offers/post-doctoral-research-fellowships/post-doctoral-research-fellowships/campaign-2014/%28view%29/details.html?nPostingTargetID=13790 (earlier application is preferred)

Inria is the biggest European public research institute dedicated to computer science. The PAROLE team in INRIA Nancy, France, gathers 20+ speech scientists with a growing focus on speech enhancement and noise-robust speech recognition exemplified by the organization of the CHiME Challenge [1] and ISCA's Robust Speech Processing SIG [2].

The boom of speech interfaces for handheld devices requires automatic speech recognition (ASR) system to deal with a wide variety of acoustic conditions. Recent research has shown that Deep Neural Networks (DNNs) are very promising for this purpose. Most approaches now focus on clean, single-source conditions [3]. Despite a few attempts to employ DNNs for source separation [4,5,6], conventional source separation techniques such as [7] still outperform DNNs in real-world conditions involving multiple noise sources [8]. The proposed postdoctoral position aims to overcome this gap by incorporating the benefits of conventional source separation techniques into DNNs. This includes for instance the ability to exploit multichannel data and different characteristics for separation and for ASR. Performance will be assessed over readily available real-world noisy speech corpora such as CHiME [1].

Prospective candidates should have defended a PhD in 2013 or defend a PhD in 2014 in the area of speech processing, machine learning, signal processing or applied statistics. Proficient programming in Matlab, Python or C++ is necessary. Practice of DNN/ASR software (Theano, Kaldi) would be an asset.

[1] http://spandh.dcs.shef.ac.uk/chime_challenge/

[2] https://wiki.inria.fr/rosp/

[3] G. Hinton, L. Deng, D. Yu, G. Dahl, A.-R. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, 'Deep neural networks for acoustic modeling in speech recognition', IEEE Signal Processing Magazine, 2012.

[4] S.J. Rennie, P. Fousek, and P.L. Dognin, 'Factorial Hidden Restricted Boltzmann Machines for noise robust speech recognition', in Proc. ICASSP, 2012.

[5] A.L. Maas, T.M. O’Neil, A.Y. Hannun, and A.Y. Ng, 'Recurrent neural network feature enhancement: The 2nd CHiME Challenge', in Proc. CHiME, 2013.

[6] Y. Wang and D. Wang. 'Towards scaling up classification-based speech separation”, IEEE Transactions on Audio, Speech and Language Processing, 2013.

[7] A. Ozerov, E. Vincent, and F. Bimbot, 'A general flexible framework for the handling of prior information in audio source separation', IEEE Transactions on Audio, Speech and Language Processing, 2012.

[8] J. Barker, E. Vincent, N. Ma, H. Christensen, and P. Green, 'The PASCAL CHiME Speech Separation and Recognition Challenge', Computer Speech and Language, 2013.

Top

6-10(2014-01-22) PhD position on Automatic analysis of affective and social behaviors in human-robot interaction, Univ Twente, The Netherlands

PhD position on Automatic analysis of affective and social behaviors in human-robot
interaction

http://www.utwente.nl/vacatures/en/

Job specification
The Human Media Interaction group at the University of Twente is looking for a PhD
candidate who will automatically analyse social interactions based on the speakers'
non-verbal behaviors in speech (paralinguistic information). The aims are to automatically
determine the quality of social interaction between the speakers (both in dialogues and
multi-party conversations) and the speakers' affective states using vocal cues.
Qualitative aspects of social interaction include, amongst others, levels of engagement,
cooperation, enjoyableness, arousal, valence and rapport.

The work will be carried out within the contexts of two European projects involving
robots, namely TERESA and SQUIRREL. In the TERESA project, a telepresence robot is
controlled by a human controller who can have robot-mediated conversations with other
humans in the vicinity of the robot. In order to know whether a specific speaker attitude
is caused by the robot's or the human controller's behavior, an assessment of the
interaction is needed. The challenges are to give a continuous assessment of the quality
of interaction under natural conditions, and to find out what non-verbal vocal cues can be
used to detect qualitative aspects of social interaction. In the SQUIRREL project,
children will be interacting with a robot that aims to encourage and help them tidy up and
put objects back in order. In order to design effective robot behaviors that encourage and
help children tidy up, an assessment of the interaction among the children and the robot
is needed: is the interaction fun, are the children engaged in the task, is one of the
children excluded in the interaction?

The work will cover a range of various tasks:

* The candidate will collect speech data by recording social interactions between adult
humans (French) and among children (German) and robots. (S)he will develop and manage
audio(visual) databases of these recorded interactions.

* The candidate will perform analyses on the non-verbal vocal behavior of the recorded
interactions. The candidate will investigate what types of qualitative and affective
aspects of social interaction are relevant in this context and annotations will be made.

* (S)he will identify relevant non-verbal vocal cues that correlate with qualitative and
affective aspects of social interaction.

* Based on these annotations, the candidate will develop algorithms to automatically
assess qualitative and affective aspects of social interaction, both in human adult and
children speech.

* The candidate is expected to present his/her work in major (international) conferences
and workshops, and to publish in relevant journals.


Your Profile

* The candidate should have fluent command of English as a written and spoken language.
Since the candidate will be working with Dutch, French and German data, knowledge of these
languages is preferable.

* The candidate has an MSc degree in Computer Science or equivalent (a degree with a
technical background in, e.g., Artificial Intelligence, Computational Linguistics).

* The candidate is interested in the research fields of speech analysis, affective
computing, social signal processing, and machine learning.

* The candidate has programming skills in one of the following languages (or equivalents):
Python, Perl, or Matlab.

Please send your application with your CV and motivation letter through the application
link before February 7, 2014. Please also include the names, email addresses, phone
numbers, and information about past working relationships of two people that we could
contact for a recommendation.

Further information about the PhD position can be given by Dr. Khiet Truong
(k.p.truong@utwente.nl) and Prof. Dr. Vanessa Evers (email: v.evers@utwente.nl).

Our offer
We offer a full-time PhD position in a dynamic and international environment. The duration
of the contract is four years. The gross salary will range from € 2.083,00 in the first
year to € 2.664,00 per month in the fourth year. Additionally, the University of Twente
provides excellent facilities for professional and personal development. In addition, we
offer a holiday allowance (amounts to 8%) and an end-of-year bonus of 8.3% and a number of
additional benefits. The labor agreements are in accordance with the CAO-NU for Dutch
universities.

The Organisation
The University of Twente.
We stand for life sciences and technology. High tech and human touch. Education and
research that matter. New technology which drives change, innovation and progress in
society. The University of Twente is the only campus university in the Netherlands;
divided over six faculties we provide more than fifty educational programmes. The
University of Twente has a strong focus on personal development and talented researchers
are given scope for carrying out pioneering research.

The faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) comprises
three disciplines that shape Information and Communication Technology. ICT is more than
communication. In almost every product we use mathematics, electronics and computer
technology and ICT now contributes to all of societies' activities. The faculty works
together intensively with industrial partners and researchers in the Netherlands and
abroad and conducts extensive research for external commissioning parties and funders. The
research which enjoys a high profile both at home and internationally, has been
accommodated in the multidisciplinary research institutes MESA+, CTIT and MIRA.

---

Top

6-11(2014-01-22) POST-DOCTORAL POSITION FOR THE PROJECT IFCASL (LORIA, NANCY, FRANCE)

POST-DOCTORAL POSITION FOR THE PROJECT IFCASL (LORIA, NANCY, FRANCE)

We invite applications for a one-year Post‐Doctoral position at the Laboratoire LORIA (Lorraine University, INRIA, CNRS, UMR 7306, France), to work on the project IFCASL (Individualised Feedback in Computer-Assisted Spoken Language learning).

•    Description
The IFCASL project is funded by the Deutsche Forschunggemeinschaft (DFG) and the French National Research Agency (ANR). It aims at increasing the usability and efficiency of computer-assisted language learning software by adapting content, feedback and exercises to individual learners in the speech dimension of a foreign language. This will be achieved by integrating the production and perception of the learner’s own speech and focusing on the French-German language pair, in both directions.

The objective is to offer feedback that relies on phonetic knowledge incorporated in the learning system and interacts relevantly with automatic speech recognition (ASR) and signal processing. This means that confidence in the results returned by ASR will be taken into account to derive diagnoses and feedback: the higher the confidence the more explicit the level of feedback.

A corpus of German recorded by French learners and a second of French recorded by German learners will be exploited to determine errors on the one hand, and to develop algorithms involved in feedback on the other hand.

•   
Job description
The post‐doctoral fellow will be mainly involved in the development of the signal processing and automatic speech recognition algorithms intended to realize the diagnosis and acoustic feedback provided to learners.

•   
Qualifications
A Ph.D. in signal processing or in computer sciences (automatic speech recognition, statistic modeling) and solid competence/experience in JAVA development are required. Experience in phonetics and speaking German and French are also welcome.

•   
Application procedure
Candidates should send a detailed CV with a list of publications, and a cover letter with statement of research interests and details of their experience in signal processing, automatic speech recognition and JAVA.
Please e-mail documents to:
Yves.Laprie@loria.fr (Yves Laprie, LORIA, Nancy, France).

Deadline for submission: March 30, 2014
Expected start date: May 2014 (There is some flexibility.)
Length of contract: 12 months
Salary: €2000/month (net)

   

Top

6-12(2014-02-18) Speech Data Evaluator for French at Google, Dublin

Speech Data Evaluator for French

Job title:

Speech Data Evaluator for French (Multiple positions)

 

Linguistic Field(s):

  • Phonetics/Phonology

  • Semantics

  • Discourse Analysis

 

Job description:

As
a Speech Data Evaluator and a native-level speaker of French, you will
be part of a team based in Dublin, processing large amounts of
linguistic data and carrying out a number of tasks to improve the
quality of Google’s speech synthesis and speech recognition in your own
language.

 

This includes:

  • classifying and annotating linguistic data

  • transcription

  • labeling text for disambiguation, expansion, and text normalization

  • providing phonetic transcription of lexicon entries according to given standards and using in-house tools

 

Job requirements:

  • native-level speaker of French (with good command of the standard dialect) and fluent in English

  • passion for language with good knowledge of orthography and grammar in the target language

  • a
    degree in a language-related field such as linguistics, language
    teaching, translation, editing, writing, proofreading, or similar

  • keen
    interest in technology and computer-literate (should feel comfortable
    using in-house tools and should have an interest in current speech,
    mobile and online technology)

  • attention to detail and good organizational skills

 

Project duration: 6-11 months (with potential for extension)

**This is not a permanent position but a contract position.**

 

For
immediate consideration, please email your CV and cover letter in
English (PDF format preferred) with 'Speech Data Evaluator [French]' in
the subject line.

 

Email Address for applications: DataOpsMan@gmail.com

Contact information: Ara Kim

Closing date: open until filled

Top

6-13(2014-02-20) PhD scholarship on deep neural networks , INRIA, Nancy, F

We are pleased to offer a PhD scholarship on deep neural networks for source separation and noise-robust ASR
http://www.inria.fr/en/institute/recruitment/offers/phd/campaign-2014/%28view%29/details.html?nPostingTargetID=14062 
 


We are looking forward to receiving applications by April 18 (please do not wait until the later deadline indicated on the website).

Top

6-14(2014-02-20) 3 positions of Maitre de conférence (lecturer) at Avignon, F

Trois postes de Maître de Conférences en informatique (section 27) sont mis au concours pour la campagne 2014 au Centre d'Enseignement et de Recherche en Informatique de l'Université d'Avignon (ceri.univ-avignon.fr).

Les personnes recrutées effectueront leur recherche au sein du LIA (lia.univ-avignon.fr).

Les profils des 3 postes, consultables sur lia.univ-avignon.fr rubrique Emplois, couvrent les thématiques du laboratoire :

- Informatique - Spécialité langage/recherche et extraction d'information  (Poste 0284 / Galaxie 4043)

- Informatique - Spécialité réseaux  (Poste 0334 / Galaxie 4045)

- Informatique - Spécialité recherche opérationnelle et optimisation (Poste 0324 / Galaxie 4044)

Contacts :

Enseignement : Corinne Fredouille corinne.fredouille@univ-avignon.fr - Directrice des Etudes du CERI et Fabrice Lefèvre fabrice.lefevre@univ-avignon.fr - Directeur du CERI

Recherche : Georges Linares georges.linares@univ-avignon.fr - Directeur du LIA et Fabrice Lefèvre fabrice.lefevre@univ-avignon.fr - Directeur du CERI

Top

6-15(2014-03-04) Speech Linguistic Project Manager - Google Speech Research, London, UK

Speech Linguistic Project Manager - Google Speech Research


Job title:

Speech Linguistic Project Manager


Location:

London, UK


Linguistic Field(s):

  • Phonetics/Phonology

  • Semantics

  • Discourse Analysis


Job description:

The
Speech Team at Google builds technologies to turn spoken input into
machine understandable format, or written text into spoken output. Our
technology is used to enable voice-based interactions in products like
Google Now, Voice Search, Dictation, Speech-to-Speech Translation,
Google Glass, and more.




As
a Linguistic Project Manager and a native-level speaker of French, you
will oversee and manage all work related to achieving high data quality
for speech projects in your own language.


You
will be part of a team based in London, managing a team of Data
Evaluators and working on a number of projects towards Speech research:
ASR, TTS, and NLP.


This includes:

  • training, managing and overseeing the work of your team

  • creating verbalisation rules, such as expanding URLs, email addresses, numbers

  • propose new projects to fulfill research needs for spoken languages around the world

  • creating annotation conventions

  • evaluating data quality

  • providing expertise on pronunciation and phonotactics

  • working with QA tools according to given guidelines and using in-house tools


Job requirements:

  • native-level speaker of French (with good command of the standard dialect) and fluent in English

  • must have attended elementary school in the country where the language is spoken

  • keen ear for phonetic nuances and attention to detail; knowledge of the language’s phonology

  • ability to quickly grasp technical concepts; should have an interest in current speech, mobile and online technology

  • excellent oral and written communication skills

  • good organizational skills

  • previous project management and people management experience

  • previous experience with speech/NLP-related projects a plus

  • advanced degree in Linguistics preferred; experience with Computational Linguistics a plus

  • also a plus: proficiency with HTML, XML, and some programming language; previous experience working in a Linux environment


Project duration: 6-11 months (with potential for extension)

**This is not a permanent position but a contract position.**


For
immediate consideration, please email your CV and cover letter in
English (PDF format preferred) with 'Speech Linguistic Project Manager
[French]' in the subject line.


Email Address for applications: DataOpsMan@gmail.com

Contact information: Ara Kim

Closing date: open until filled
Top

6-16(2014-03-04) Doctoral student position , Aalto University, Finland

Doctoral student position in an interdisciplinary speech technology project “Computational Modeling of Language Acquisition”

Job description:
The Speech Technology Team of Aalto University offers a full-time doctoral student position on computational modeling of language acquisition. Those who wish to do their master’s thesis on the topic and are willing to pursue post-graduate studies after their graduation are also welcome to apply.
The high-level goal of the research project is to understand how human children learn to understand and produce speech, and how computers could be programmed with similar learning skills in order to outperform the classical manually engineered speech recognition systems. In short-term, the focus is on the development of ecologically plausible computational models of different aspects of human language processing (perception, production, multimodal interactions) and evaluating these models with respect to data from behavioural studies. The research is simultaneously concerned with the development and application of low-level machine learning and signal processing algorithms and on the development of high-level models of language learning, making the work highly interdisciplinary, diverse and challenging.
The more specific content of the current position is not fixed in advance, but will be planned together with a successful applicant. The focus can be more on the technical side (machine learning/signal processing algorithm development), on the behavioural side (collecting and modelling behavioural data), or both.

Requirements:
Due to the interdisciplinary nature of the work, we are looking for an applicant with a strong background, skills and a burning interest in one or more of the following fields: speech/signal processing, auditory modeling, speech acoustics, machine learning, cognitive science, cognitive psychology, computational linguistics, artificial intelligence, or mathematics.
A successful applicant will have a M.Sc. (tech.) or an equivalent degree in a relevant field or has nearly completed the degree, has good programming skills (e.g., MATLAB, Java or C) and is a fluent user of English (both written and verbal). Capability for self-driven independent and productive work is a must. Basic or advanced knowledge in signal processing, machine learning, and/or statistics are a significant advantage.

Job details:
The current work will take place in a project Computational Modeling of Language Acquisition, funded by the Academy of Finland. The first contract will be a 6–month trial period for doctoral students or 6 months for the M.Sc. thesis work. Extension up to a total of 2.5 years is envisioned upon successful performance. The work will take place in the Department of Signal Processing and Acoustics of Aalto ELEC.

Salary:
Salary level will be based on the local-agreement salary system of Aalto University.

How to apply:
Please send your application to D.Sc. Okko Räsänen (okko.rasanen@aalto.fi) by email. The deadline for applications is 31.4.2014. Please include at least the following documents in your application: a cover letter describing your background and motivation for the position, CV, a transcript of bachelor and master’s level study records, and possible letters of recommendation.

For more information, please contact:
D.Sc. Okko RäsänenorProf. Unto K. Laine
okko.rasanen@aalto.fiunto.laine@aalto.fi
+358-50-441 9511+358-50-593 0251

Top

6-17(2014-03-04) Postdoctoral fellow in the area of phonetics, Max Planck Institute, Leipzig, Germany

Max Planck Institute for Evolutionary Anthropology, Leipzig, Germany

 

Announcement of Vacancy

 

The Department of Linguistics at the Max Planck Institute in Leipzig has a vacancy for a postdoctoral fellow in the area of phonetics.

 

In order to understand the abstract structure underlying the movements of articulators involved in speech sound production, the department’s phonetics lab is developing methods aimed at detecting the coupling relations between the dynamical systems involved. This work is based on a variant of joint recurrence analysis which is compatible with the uncontrolled manifold theory of synergies in intentional dynamics. The methods will be applied to explore the abstract coupling links underlying the coordination between the behavior of the larynx and the behavior of oral articulators.

 

The successful candidate will be involved in the conceptual design and in the development of analytical tools. This includes the areas of joint recurrence analysis, recurrence network approaches, and procedures for building surrogate databases for testing the significance of the observed relations.

 

The one-year non-renewable position ends no later than May 31, 2015.

 

Prerequisites for an application are a PhD and knowledge of dynamical systems theory as well as of information theory (as shown by relevant publications or by his/her academic curriculum), with an interest in their application to real datasets. Programming skills (preferably Matlab or C++) are required. Knowledge of recurrence analysis methods and of Bayesian statistics is welcome.

 

The salary is according to the German public service pay scale (TVöD). The Max Planck Society is concerned to employ more disabled people; applications from disabled people are explicitly sought. The Max Planck Society wishes to increase the proportion of women in areas in which they are underrepresented; women are therefore explicitly encouraged to apply.

 

Applicants are requested to send their complete dossier (including curriculum vitae, description of research interests, names and contact details of two referees, and a piece of written work on one of the relevant topics) to:

 

Max Planck Institute for Evolutionary Anthropology

Personnel Department

Prof. Dr. Bernard Comrie

Code word: Postdoc Phonetics

Deutscher Platz 6

D-04103 Leipzig, Germany

 

Application will be received until the position is filled.

 

Please address questions to Dr. Sven Grawunder <grawunder@eva.mpg.de>.

Information on the institute is available at http://www.eva.mpg.de/.

 

Top

6-18(2014-03-05) PhD research fellowship at Université de Sherbrooke, Canada

 

Ver. 2014-03-03

Ph.D. project offer

Title

Development of speech coding algorithms inspired by the central auditory system

Description

The central auditory system has many characteristics that could foster the development of improved speech coders. The objective of this research project is to develop speech coding algorithms that are inspired by the central auditory system. This work will make use of the current knowledge in neural signal processing by the central auditory system as well as of several metrics developed for the objective evaluation of speech processing algorithms. It will allow the study of new paradigms that will lead to the development of novel speech coding algorithms. The research will be conducted jointly in the Speech and Audio Processing Laboratory and the Computational Neuroscience and Intelligent Signal Processing Research Group at the Université de Sherbrooke, Sherbrooke, Canada. A financial support is expected.

Requirements

Excellent academic record.

 Strong background in speech processing.

 Excellent ability to communicate in English. Knowledge of French is considered an advantage.

 Interest in neuroscience.

The Université de Sherbrooke is a French-speaking institution located in the province of Quebec, Canada, and the heart of an international research pole. It is host to more than 40 000 students from over 120 different countries worldwide. (Source: UdeS)

For more information: Eric Plourde, Eng., Ph.D.

Roch Lefebvre, Eng., Ph.D.

Department of Electrical and Computer Engineering

Department of Electrical and Computer Engineering

Faculty of Engineering

Faculty of Engineering

Université de Sherbrooke

Université de Sherbrooke

Sherbrooke, Quebec Canada

Sherbrooke, Quebec Canada

+819-821-8000, # 63255

eric.plourde@usherbrooke.ca

+819-821-8000, # 62134

roch.lefebvre@usherbrooke.ca

www.gel.usherbrooke.ca/plourde/english.html

www.usherbrooke.ca/gelecinfo/fr/departement/profs/lefr-en/

Top

6-19(2014-03-06) 1 postdoc and 1PhD at INRIA, Nancy, F
 
 
*** Postdoc #1
Post-doctoral Fellow - INRIA - Nancy, France
 
Title : Accurate 3D Lip modeling and control in the context of animating a 3D talking head
 
The goal of this work is to develop an accurate 3D lip model that can be integrated within a talking head. A control model will also be developed. The lip model should be as accurate dynamically as possible. When designing this model, the focus will be on the dynamics. For this reason, one can start from a static 3D lip mesh, using a generic 3D lip model, and then we will use MRI images or 3D scans to obtain more realistic shape of the lips. To take into account the dynamic aspect of the lip deformation, we will use an articulograph (EMA) and motion capture technique to track sensors or markers on the lips. The mesh will be adapted to this data. 
To control the lips, we will consider allowing a skeletal animation to be controlled by the EMA sensors or motion capture markers, using inverse kinematic technique, widely used in 3D modeling. In line with conventional skeletal animation, an articulated armature rigged inside the mesh is mapped to vertex groups on the lip mesh by a weight map that can be defined automatically from the envelope of the armature’s shape and manually adjusted if required, where manipulating the armature’s components deforms the surrounding mesh accordingly.
The main challenge is to find the best topology of the sensors or markers on the lips, to be able to better capture accurately its dynamics. The main outcome is to accurately model and animate the lips based on articulatory data. It is very important to have readable lips in that can be lip-read by hard-of-hearing people. 
 
 
For full description and to apply, please visit this website:
 
The applications will be considered as soon as received.
 
 
Slim Ouni
University of Lorraine
Parole - Inria Nancy -Grand Est
 
************************************************************
PhD #1
Position type: PhD Student - INRIA - Nancy, France

Title: Emotion modeling during expressive audiovisual speech
 
The goal of this thesis is to study the expressivity from articulatory and visual points of view. The articulatory and facial gestures will be characterized for the different sounds of speech (called phonemes) in the different expressive contexts. The goal is to determine how facial expressions interact with speech gesture (lips, tongue, face and acoustics), and how this is embedded within the phoneme articulation and their acoustic consequences. The quantification of the intensity of an expression during a given phoneme (or sequence of phonemes) articulation needs to be determined. One important objective of this work is to develop an expressive control model, which describes the interaction of the facial expressions with audiovisual speech.
 
To achieve these goals, two corpora will be acquired using electromagnetography (EMA) and motion capture techniques synchronously with acoustics. The EMA is the technique that uses electromagnetic sensors, glued on the tongue, teeth, lips and eventually the face, that represent 3D positions, and two angle orientations. We will use a marker-less motion capture that allows retrieving the dynamics of the face due to speech and expressivity. The corpora will cover sentences pronounced in several emotional contexts. These corpora provide the articulatory trajectories of the tongue and the lips in addition to the acoustic signal. The acquired data will be processed and analyzed, and the control model will be developed based on the results of this analysis.
 
For full description and to apply, please visit this website:
 
The applications will be considered as soon as received.
 
Slim Ouni
University of Lorraine
Parole - Inria Nancy -Grand Est
Top

6-20(2014-03-07) Post-doc position at LORIA (Nancy, France)

Post-doc position at LORIA (Nancy, France)

Framework of ANR project ContNomina

The technologies involved in information retrieval in large audio/video databases are often based on the analysis of large, but closed, corpora, and on machine learning techniques and statistical modeling of the written and spoken language. The effectiveness of these approaches is now widely acknowledged, but they nevertheless have major flaws, particularly for what concern proper names, that are crucial for the interpretation of the content.

In the context of diachronic data (data which change over time) new proper names appear constantly requiring dynamic updates of the lexicons and language models used by the speech recognition system.

As a result, the ANR project ContNomina (2013-2017) focuses on the problem of proper names in automatic audio processing systems by exploiting in the most efficient way the context of the processed documents. To do this, the postdoc student will address the contextualization of the recognition module through the dynamic adjustment of the language model in order to make it more accurate.

Post-doc subject

The language model of the recognition system (n gram learned from a large corpus of text) is available. The problem is to estimate the probability of a new proper name depending on its context. Several tracks will be explored: adapting the language model, using a class model or studying the notion of analogy.

Our team has developed a fully automatic system for speech recognition to transcribe a radio broadcast from the corresponding audio file. The postdoc will develop a new module whose function is to integrate new proper names in the language model.

Required skills

A PhD in NLP (Natural Language Processing), be familiar with the tools for automatic speech recognition, background in statistics and computer program skills (C and Perl).

Post-doc duration

12 months from June 2014 (these is some flexibility)

Localization

Loria laboratory, Speech team, Nancy, France

Contacts

Irina.illina@loria.frdominique.fohr@loria.fr

Candidates should email a letter of application, a detailed CV with a list of publications and diploma

Top

6-21(2014-03-07) MCF en informatique pour les Sciences Humaines, Université Paris Sorbonne.

Un poste de MCF en informatique pour les Sciences Humaines est ouvert à l'Université Paris Sorbonne. Le candidat enseignera l’Informatique dans les différentes formations de licence et de master du département d’Informatique, Mathématiques et de Linguistique appliquées. Il devra s'inscrire dans un ou plusieurs axes de l'équipe de linguistique computationnelle (www.stih.paris-sorbonne.fr/) : Sémantiques et connaissances, Paralinguistique de la parole et du texte, Jugements d’évaluation, opinions et sentiments.

Personne à contacter : Claude.Montacie@Paris-Sorbonne.fr

Top

6-22(2014-03-08) Senior Technical Engineer/Scientist (Software team Manager) at ELDA

The European Language resources Distribution Agency (ELDA), a company specialized in Human Language Technologies within an international context, acting as the distribution agency of the European Language Resources Association (ELRA), is currently seeking to fill an immediate vacancy for Senior Technical Engineer/Scientist (Software team Manager) position.

Under the supervision of the CEO, the responsibilities of the Senior Technical Engineer/Scientist include managing of a small development team, designing/specifying tools and software components for Language Resources, production frameworks and platforms, carrying out quality control and assessment. He/she will be in charge of renovating the current language resources production workflows. This yields excellent opportunities for young, creative, and motivated candidates wishing to participate actively to the Language Engineering field. He/she will be in charge of conducting the activities related to language resources and Natural Language Processing technologies. The task will mostly consist in managing language resources production projects and co-ordinating ELDA’s participation in R&D projects while being also hands-on whenever required by the development team.

Profile :

    Good knowledge of Linux and open source software
    Proficiency in Python, Django, PhP, Perl, CSS
    Proficiency in Django-CMS is a plus
    Good knowledge of e-commerce development (Python/Django-oriented)
    Proficiency in French and English
    Dynamic and communicative, flexible to combine and work on different tasks
    Experience with technology transfer projects, industrial projects,collaborative projects within the European Commission or other international frameworks
    Good knowledge of the Language Technology area is a plus
    Ability to work independently and as part of a team, in particular the ability to supervise members of a multidisciplinary team
    Citizenship of (or residency papers) a European Union country
    Applications will be considered until the position is filled. The position is based in Paris.

Salary : Commensurate with qualifications and experience.

Applicants should email a cover letter addressing the points listed above together with a curriculum vitae to :

Khalid Choukri
ELRA / ELDA
9, rue des Cordlières
75013 Paris
FRANCE
Fax : 01 43 13 33 30
Mail : job@elda.org


Please check out our other vacant positions:

Top

6-23(2014-03-08) PhD position in spoken dialogue systems research, Charles University, Prague, CZ
PhD position in spoken dialogue systems research
 
Applications are invited for a PhD fellowship in the area of statistical spoken dialogue systems funded by the Czech Government. The student will join the Institute of Formal and Applied Linguistics, Charles University in Prague, Czech Republic with an anticipated start date of October 1st, 2014.
 
Topic description: In recent years, it has been suggested that statistical approach to spoken dialogue system offer a framework to naturally handle inherent uncertainty in the human speech. The two main advantages of statistical methods are increased robustness in noisy conditions and more natural behaviour learnt from data. However, the current methods need large corpora effectively preventing these methods to be used for complex dialogue systems occurring in real-life. The successful PhD candidate will investigate and implement statistical models and methods with the aim of increasing the efficiency of the learning process and reducing the need for large corpora. The conducted research will cover areas of spoken language understanding, dialogue management, and natural language processing. 
 
Skills: The candidate should hold a master degree in a relevant area, such as computer science, mathematics, engineering  or linguistics. A strong mathematical background, excellent programming skills (e.g. C/C++, Java, MATLAB, and various scripting languages under Linux environment), aptitude for creative research and autonomy are expected. Experience in machine learning, Bayesian methods, and natural language processing is a plus.
 
The Institute of Formal and Applied Linguistics is a top-level research group working in the area of computational linguistics and natural language processing. During the fellowship, there will be good opportunities to attend international conferences and workshops. The formal applications should be submitted before June 1. Prospective candidates are strongly encouraged to contact Dr Filip Jurcicek (jurcicek@ufal.mff.cuni.cz) as soon as possible to obtain details about the application process, the institute, and the research opportunities. 
 
Additional information is available at https://ufal.mff.cuni.cz/filip-jurcicek/jobs.
Top

6-24(2014-03-12) Researchers in Speech and dialog at IKERBASQUE, Bilbao, Spain
Ikerbasque would like to inform you that we have launched a new international call to reinforce research and scientific career in the Basque Country. We offer:
 
 
·          25 positions for Promising Researchers Ikerbasque Research Fellows  
o    5 year contracts
o    PhD degree between Jan2004-Dec2011
o    Support letter from the host group is mandatory
o    Deadline: March 31st at 13:00 CET
 
For further information, use this link: www.ikerbasque.net
 
We would appreciate your help in disseminating this information, in case you know about any colleague that could be interested and meets the requirements of the call.
 
 
 
IKERBASQUE
Basque Foundation for Science

Professor M. Inés Torres
PR&Speech Technology
Dpto. Electricidad y Electrónica
Fac. Ciencia y Tecnología - UPV/EHU
Apdo. 644 - 48080 Bilbao (Spain)
Phone: +34 94 601 2715
e_mail: manes.torres@ehu.es


Top

6-25(2014-03-17) Post Doctoral Position Iceland

Applications are invited for a postdoctoral position in the area of speech processing 
Post Doctoral Position in Speech Processing    
for cognitive workload monitoring.  We are looking for an engineer/computer 
scientist with an experience in machine learning, statistics, and speech signal 
processing or in closely related fields. The main aim of the project is to develop a 
pattern recognition software that detects and monitors cognitive workload of air 
traffic controllers from their speech commands, video recordings and other 
observations.  This is achieved with recordings of participants during cognitive 
workload experiments and with with transferring the technology to simulated air 
traffic control environment. A successful applicant will be expected to lead this work 
and assist in the supervision of doctoral and master students working in this area.     
 
Applicants should have received a doctoral degree in engineering, computer science 
Qualifications:   
or a related discipline, or completion of all requirements for the degree should be 
expected prior to the starting date. A successful applicant will have an experience in 
machine learning, statistics, speech processing or closely related fields and be able 
to implement signal processing and machine learning procedures in an appropriate 
environment.   
 
Reykjavik University is an international university located at the heart of Reykjavik, 
About Reykjavik University:   
the capital of Iceland. It was established in 1998 and it is the largest technical 
university in Iceland.  RU places a strong emphasis on research and publishes more 
scientific articles in its fields of expertise than any other university in the country.  
The university has developed a productive and appealing research environment for 
Icelandic and foreign scientists. Approximately 140 academic employees (assistant 
professors, associate professors, professors, adjuncts, postdoctoral fellows, guest 
professors, and other specialists) currently work at RU on various research projects 
in collaboration with both domestic and international research institutions and 
companies.   
 
The appointment is available immediately and is for two years. The participant will 
Appointment:   
be selected based on academic records, recommendations, research interests and 
compatibility of background. The salary is determined from the guideline of the 
Icelandic Research Fund (http://www.rannis.is) for post- doctoral research 
associates.   
 
Electronic applications, including a cover letter, a CV and the details of two referees, 
How to apply:   
should be sent to dr. Jon Gudnason (email: jg@ru.is) and dr. Kamilla Johannsdottir 
(kamilla@ru.is). 

Top

6-26(2014-03-23) Post-doc position at LIMSI-CNRS in the Spoken Language Processing group

Post-doc position at LIMSI-CNRS in the Spoken Language Processing group

A post-doc position is proposed at LIMSI-CNRS (Orsay, France - http://www.limsi.fr), in the context of the ANR-funded CHIST-ERA CAMOMILE Project (Collaborative Annotation of multi-MOdal, MultI-Lingual and multi-mEdia documents - http://www.chistera.eu/projects/camomile).

Context of the project

Human activity is constantly generating large volumes of heterogeneous data, in particular via the Web. These data can be collected and explored to gain new insights in social sciences, linguistics, economics, behavioural studies as well as artificial intelligence and computer sciences.
In this regard, 3M (multimodal, multimedia, multilingual) data could be seen as a paradigm of sharing an object of study, human data, between many scientific domains. But, to be really useful, these data should be annotated, and available in very large amounts. Annotated data is useful for computer sciences which process human data with statistical-based machine learning methods, but also for social sciences which are more and more using the large corpora available to support new insights, in a way which was not imaginable few years ago. However, annotating data is costly as it involves a large amount of manual work, and in this regard 3M data, for which we need to annotate different modalities with different levels of abstraction is especially costly. Current annotation framework involves some local manual annotation, with the help sometimes of some automatic tools (mainly pre-segmentation).
The project aims at developing a first prototype of collaborative annotation framework on 3M data, in which the manual annotation will be done remotely on many sites, while the final annotation will be localized on the main site. Furthermore, with the same principle, some systems devoted to automatic processing of the modalities (speech, vision) present in the multimedia data will help the transcription, by producing automatic annotations. These automatic annotations are done remotely in each expertise point, which will be then combined locally to produce a meaningful help to the annotators.
In order to develop this new annotation concept, we will test it on a practical case study: the problem of person annotation (who is speaking?, who is seen?) in video, which needs collaboration of high level automatic systems dealing with different media (video, speech, audio tracks, OCR, ...). The quality of the annotated data will be evaluated through the task of person retrieval.
This new way to envision the annotation process, should lead to some methodologies, tools, instruments and data that are useful for the whole scientific community who have interest in 3M annotated data.

Requirements and objectives

A PhD in a field related to the project (speech processing, computer vision or machine learning) is required. The candidate will perform research on multimodal person recognition in videos (speaker recognition, face recognition or multimodal fusion) and will also be involved with the partners in the development of the distributed annotation framework. Knowledge of JavaScript and Python programming languages is needed for working on this framework. Salary will follow CNRS standard rules for contractual researchers, according to the experience of the candidate.

Contacts

  • Claude Barras (Claude.Barras [at] limsi.fr)
  • Hervé Bredin (Herve.Bredin [at] limsi.fr)
  • Gilles Adda (Gilles.Adda [at] limsi.fr)

Agenda

  • Opening date: May 2014
  • Duration: 18 months

   

Top

6-27(2014-03-25) Offre de thèse en France

 


Sémiologie  sonore  pour  l'analyse  spatiale  et  la
représentation cartographique

 

                                              
Directeurs de thèse : JOSSELIN Didier  & ALTMAN Eitan

                                                                    
Membres extérieurs du comité de thèse : BONIN Olivier ,  
BRESSON Jean

1. Laboratoire d'Informatique d'Avignon (LIA), Avignon
2. IFSTTAR – AME-LVMT Champs sur Marne, Marne la Vallée
3. UMR ESPACE, Avignon
didier.josselin@univ-avignon.fr
4. IRCAM, Paris
5. INRIA, Sophia-Antipolis

MOTS-CLÉS :  CARTOGRAPHIE,  MUSIQUE,  GEOMATIQUE,  ANALYSE  SPATIALE,  COMPOSITIONS,
PARTITIONS


Résumé :
La  recherche  proposée  consiste  à  poser  les  fondations  d'une  sémiologie  pour  la
représentation cartographique qui ne soit plus basée exclusivement sur la graphique,
mais sur le son, voire la musique au sens large.
Cette recherche est fondamentale puisqu'elle doit appréhender la dialectique entre la
méthodologie cartographiquee et la théorie de la musique, en appréhendant ce que la
carte  apporte  à  la  musique  et  réciproquement,  en  dégageant  les  différentes
dimensions partagées par les deux approches.
Potentiellement,  elle  a  aussi  une  portée  pratique,  puisqu'elle  peut,  d'une  part,
améliorer la compréhension de la lecture de la carte en ajoutant l'audition à la vue
dans les processus d'analyse  spatiale de données géographiques. Elle peut, à terme,
déboucher  sur  des  applications  de  reconnaissance  dynamique  d'environnement  par
des personnes malvoyantes ou à mobilité réduite, via les cartes mentales.
Ce  sujet  de  recherche  est  ouvert  à  différentes  disciplines,  comme  la  géographie
(géomatique  notamment),  les  sciences  de  l'information  et  de  la  communication,
musicologie, sciences cognitives.

1. Contexte et rationalité

   Depuis les travaux précurseurs  de J. Bertin (1975) en sémiologie graphique,  la
cartographie  a  largement  évolué  (Escobar  et  al.,  2008)  sur  deux  aspects  en
particulier : l'interactivité et l'accessibilité en ligne. On parle depuis quelques années
de  cartographie  en  mouvement  (Mac  Eachren,  1995,  Josselin  &  Fabrikant,  2003),
c'est à dire animée, multimédia (notamment en ligne)  ou interactive  (Cartwright et
al, 2007).

   La  cartographie  peut  être  descriptive,  dans  le  sens  où  elle  sert  à  observer  des
phénomènes se déroulant dans le temps. Mais elle devient rapidement exploratoire,
voire  se  dote  d'un  pouvoir  explicatif,  par  la  capacité  de  ses  outils  à  mettre  en
interaction  différentes  dimensions  ou  points  de  vue.  À  ce  titre,  l'analyse  spatiale
exploratoire  (Andrienko,  2006)  s'est  largement  développée  et  ouvre  de  vastes
horizons scientifiques, technologiques et d'usage. En lien direct avec les cartes et la
géographie,  les graphiques  et les indices  statistiques  constituent  en  effet  autant  de
résumés  des données,  prises dans leur ensemble ou via des sélections appropriées.
Ces méthodes d'analyse constituent de puissants outils d'investigation ou de fouille
de données spatiales.

   Dans  les  outils  de  cartographie,  le  recours  à  la  dimension  visuelle  des
représentations  statistiques  reste  prégnant.  Cependant,  d'autres  voies
complémentaires existent, tels que le son ou la musique. Par exemple, le mouvement
du  « soundscape »  (paysage  sonore)  utilise  les  ambiances  sonores  pour  donner  du
sens  aux  lieux  et  aux  environnement  (Murray  Schafer  1969).  D'autres  auteurs
proposent de simples cartographies  des sons (Schiewe  & Kornfeld  2009). Dans ce
cas, les « signatures sonores » marquent et caractérisent les lieux de façon explicite.
Toutefois, elles ne sont pas utilisées pour mettre en évidence des discontinuités, des
gradients  ou  des  structures  dans  l'espace  (de  mobilité,  par  exemple).  Pourtant,
l'association  des  capacités  cognitives  visuelles  et  auditives  ne  peut  qu'améliorer
notre capacité à analyser  les données géographiques, d'autant plus lorsqu'elles sont
complexes.
   L'utilisation de représentations spatiales et de calculs spatiaux pour les structures
musicales  est  ainsi  un  domaine  en  plein  essor.  On  pourrait  étudier  le  problème
inverse :  à  partir  d'une  structure  spatiale  extraite  d'une  carte  ou  d'une  image,
reconstituer  les  contraintes  musicales  (harmoniques,  mélodiques,  rythmiques)
associées.  On  serait  alors  dans  une  démarche  d'aide  à  la  composition  musicale
(Adhitya  and  Kuuskankare,  2012).  Par  le  biais  de  règles  prédéterminées  ou  avec
l'assistance  d'un  utilisateur,  on  pourra  aller  jusqu'à  la  sonorisation  d'images  ou  de
cartes.  Au-delà de cet objectif, le rapprochement  entre analyse  musicale et analyse
spatiale privilégie souvent un sens   : les représentations musicales s'enrichissent de
représentations  spatiales.  Enrichir  le  domaine  de  l'analyse  spatiale  par  des
techniques  issues  de  l'analyse  musicale  est  une  perspective  intéressante  et
complémentaire. Cette thèse s'inscrit dans cette seconde approche.

2. Orientation de la thèse


2.1. Objectifs

   À notre connaissance, il n'existe pas aujourd'hui de sémiologie sonore éprouvée
et  consensuelle  permettant  de  réaliser  un  lien  symbolique  non  équivoque  entre
représentation sonore et représentation cartographique. Existe-elle  in fine ? Quelles
en  sont  les  dimensions ?  Comment  la  construire  et  avec  quelles  méthodes  ?  C'est
tout l'enjeu de ce sujet de thèse, à l'interface entre les sciences de la communication,
la géographie et la géomatique, la musicologie et les sciences cognitives. À l'instar
des  travaux  de  Bertin  sur  la  sémiologie  graphique  et  sur  tous  ses  développement
consécutifs,  cette  thèse  doit  permettre  de  poser  les  bases  d'une  sémiologie  sonore
dédié à la représentation et à l'analyse spatiales.

   Les objectifs généraux de cette recherche sont :

    •   d'évaluer en quoi et de quelle façon le son peut apporter une amélioration
         des méthodes d'analyse spatiale ;
    •   de  rechercher,  dans  la théorie  de  la  musique,  ce  qui  est mobilisable  pour
         représenter  des  portions  typiques  et  structurées  (patterns)  d'espaces
         géographiques ;
    •   d'appréhender  l'aspect  numérique  et  mathématique  de  la  musique  pour
         tenter  de  poser  les  bases  d'une  sémiologie  sonore  signifiante  (pour  une
         culture musicale donnée) ;
    •   de  réfléchir  aux  méthodologies  informatiques  permettant  le  dépôt  ou
         l'exploration des cartes et d'images géographiques par les utilisateurs.


2.2. Des dimensions partagées par la carte et la musique

   La/le doctorant(e) devra appréhender la musique à travers diverses composantes
intéressantes pour l'analyse spatiale (non exclusives) :

 
 
    •   Composantes    sonores :    intensité (puissance,    vélocité,    latence),
         hauteur/degré  (fréquence,  longueur  d'onde,  période),  timbre  (perception,
         émission, grain) ;

    •   Composantes  de  partition  :  durée,  tempo,  séquence  rythmique,  partition
         graphique  contrainte  (portée,  mesures,  systèmes)  ou  non  (continuités  de
         représentation) ;

 
 
    •   Composantes harmoniques : accords, gammes, tonalités, modes ;

    •   Composantes  libres  :  interprétation,  orchestration  (taille,  instruments),
         improvisation,  « sound-painting »,  enregistrement  et  apprentissage
         dynamiques, adaptation du musicien au contexte.

   Elle/il devra mettre en regard ces composantes avec la carte, qui peut ainsi entrer
en résonance avec ces différentes dimensions :

 
    •   Composantes sonores : la description des observations spatiales et de leurs
         attributs ;

    •   Composantes  de  partition  :  aspects  temporels  de  l'analyse  spatiale
         permettant  de  gérer  des  séquences  d'exploration  des  cartes  ou  des
         phénomènes dans le temps ;

 
    •   Composantes harmoniques : les patterns spatiaux (structures et associations
         spatiales)  peuvent  correspondre  à  une  dimension  compositionnelle  pour
         identifier et construire des objets composites dans l'espace géographique ;

    •   Composantes  libres  :  un  cheminement  (festif  ou  flâneur)  de  l'explorateur
         dans l'espace de représentation ou l'espace géographique peut constituer un
         espace de liberté et d'interprétation.


3.  Déroulement de la thèse

   D'une  part,  les  approches  méthodologiques  mobilisables  dans  ce  projet  sont
largement ouvertes. Elles dépendront du profil du / de la candidat(e), qui pourra être
issu(e)  des  différentes  disciplines :  géographie,  géomatique,  sciences  de
l'information  et  de  la  communication,  musicologie,  culture  et  communication,
sciences cognitives.

   D'autre part, la thèse se déroulera en trois phases :

   Un  premier  volet,  assez  théorique  (état  de  l'art),  consiste  à  recenser  les
différentes caractéristiques de la musique et en extraire celles qui peuvent constituer
des références sémiologiques sonores ou musicales. On pourra ici s'appuyer  sur les
théories (autour) de la musique et sur les dimensions de l'analyse spatiale.

   Un  second  volet,  méthodologique,  permet  de  construire  des  protocoles
expérimentaux robustes pour évaluer/valider ces références afin de dévoiler ce que
le  son ou  la  musique  produits suscitent  en termes  d'objets  géographiques  dans un
contexte culturel donné (ancrage des symboles, aspects cognitifs).

   Un  troisième  volet,  plus  technique,  vise  à  mettre  en  oeuvre  une  cartographie
sonore  dans  un  environnement  cartographique  standard  (Système  d'Information
géographique interfacé à des outils d'analyse musicale), reposant sur les conclusions
des deux premiers volets.

    Dans tous les cas, le/la candidat(e) devra être très intéressé(e) par le domaine de
la  musique,  être  capable  d'appréhender  des  applications  informatiques  simples
(musicales  et  cartographiques)  et  de  faire  coopérer  des  logiciels  de  musique  et  de
cartographie en parfaite interopérabilité. La pratique ou la connaissance approfondie
de la musique serait un plus.

 

4.  Modalités

   Les candidat(e)s doivent contacter rapidement Didier Josselin pour présenter leur
profil,  leur  motivation  et  la  façon  dont  ils pensent  appréhender  ce  sujet  de  thèse  :
didier.josselin@univ-avignon.fr (04 90 84 35 74 ou 06 07 40 69 38). Didier Josselin
est directeur de recherche en Géomatique à l'UMR ESPACE et chercheur associé au
LIA. Eitan Alman est directeur de recherche sur les Réseaux à l'INRIA/LIA.

   Les  candidatures  d'étudiant(e)s  diplômé(e)s  ayant  des  déficiences  physiques
(mal-voyance  ou handicap  physique)  seront étudiées  en priorité sur le projet et en
exclusivité  pour  l'appel  spécifique  à  bourses  de  thèse  du  Ministère  fléché
« handicap ». Elles doivent contacter Didier Josselin impérativement avant la fin du
mois de Mars.

   Les autres candidat(e)s peuvent postuler sur la bourse de thèse Agorantic après
avoir également contacté D. Josselin : http://ed537.univ-avignon.fr/.

   La thèse sera réalisée au sein de l'ED 537 Culture & Patrimoine en Géographie
(SHS).  Deux  laboratoires  de  l'Université  d'Avignon  seront  impliqués :  UMR
ESPACE et LIA. Les laboratoires IFSTTAR et IRCAM sont partenaires du projet de
recherche englobant (CartoMuse). Une cotutelle peut être envisagée selon les profils
et souhaits des candidat(e)s.


5. Bibliographie indicative

Alayrangues  Sylvie,  Daragon  Xavier,  Lachaud  Jacques-Olivier,  Lienhardt  Pascal  (2008).
   Equivalence  between  Closed  Connected  n-G-Maps  without  Multi-Incidence  and  n-
   Surfaces,  Journal of Mathematical Imaging and Vision, Volume  32 Issue  1, pp. 1 – 22,
   Kluwer

Adhitya1  Sara  and  Kuuskankare  Mika  (2012).  SUM:  from  Image-based  Sonification  to
   Computeraided Composition, 8 pages, CMMR, 2012, London

Andrienko N. & Andrienko G. (2006), Exploratory Analysis of Spatial and Temporal Data: A
   Systematic Approach, Springer.

Bertin  J.  (1975),    La  Graphique  et  le  traitement  graphique  de  l'information,  Paris,
   Flammarion.

Cartwright W., Peterson M.P., Gartner G. (Eds) (2007), Multimedia cartography, Springer.

Escobar  Francisco,  Cauvin  Colette,  Serradj  Aziz,  (2008),  Cartographie  thématique  en  5
   volumes  (volume  1.  Une  nouvelle  démarche.  la  cartographie,  discipline  scientifique  en
   évolution;  volume  2.  Des  transformations  incontournables.  une  permanence  :  la
   transformation  sémiotique;  volume  3.  Méthodes  quantitatives  et  transformations
   attributaires. de la description à la généralisation d'une variable attributaire z; volume 4.
   Des transformations renouvelées. transformations cartographiques de position; volume 5.
   Des  voies  nouvelles  à  explorer.  les  révolutions  technologiques  et  leurs  conséquences
   conceptuelles et pratiques). Hermès-Lavoisier, Traité IGAT Série Aspects fondamentaux
   de l'analyse spatiale


Josselin D. & Fabrikant S. (Eds)  (2003), N° spécial « cartographie animée et interactive »,
   vol. 13, n°1/2003, Revue Internationale de Géomatique, Hermès, Lavoisier, Paris.

Josselin  D.   (2011),  Spatial  analysis  using  sonorous  cartography.  Some  propositions,
   ICC'2011, Paris, 3-8 July 2011.

Josselin  D.  (2005),  Interactive  Geographical  Information  System  using  LISPSTAT  :
   prototypes and applications. Journal of Statistical Software. Volume 13, Issue 6

Mac  Eachren  A.  (1995),  How  Maps  Work:  Representation,  Visualization,  and  Design,
   Guilford Press, NY.

Murray Schafer R. (1969),  The New Soundscape, Don Mills, Toronto.

Schiewe  J.,   Kornfeld  A.-L.  (2009),  Framework  and  Potential  Implementations  of  Urban
   Sound  Cartography,  12th  AGILE  International  Conference  on  Geographic  Information
   Science 2009, 8 pages.

Tymoczko Dmitri (2012). The Generalized Tonnetz, Journal o f music theory, 56:1, pp. 1-52.

Top

6-28(2014-03-27) Post doc in Grenoble (F)

Speech Unit(e)s

The multisensory-motor unity of speech

Understanding how speech unites the sensory and motor streams,

And how speech units emerge from perceptuo-motor interactions

 

ERC Advanced Grant, Jean-Luc Schwartz, GIPSA-Lab, Grenoble, France

 

 

Proposal for a post-doc position beginning in September 2014: “The informational structure of audio-visuo-motor speech”

 

Context

The Speech Unit(e)s project is focused on the speech unification process associating the auditory, visual and motor streams in the human brain, in an interdisciplinary approach combining cognitive psychology, neurosciences, phonetics (both descriptive and developmental) and computational models. The framework is provided by the “Perception-for-Action-Control Theory (PACT)” developed by the PI (Schwartz et al., 2012).

PACT is a perceptuo-motor theory of speech communication connecting, in a principled way, perceptual shaping and motor procedural knowledge in speech multisensory processing. The communication unit in PACT is neither a sound nor a gesture but a perceptually shaped gesture, that is a perceptuo-motor unit. It is characterized by both articulatory coherence – provided by its gestural nature – and perceptual value – necessary for being functional. PACT considers two roles for the perceptuo-motor link in speech perception: online unification of the sensory and motor streams through audio-visuo-motor binding, and offline joint emergence of the perceptual and motor repertoires in speech development.



Objectives of the post-doc position

In a multisensory-motor context such as the present one, a major requirement concerns a better knowledge of the structure of the information. Speech scientists have acquired a very good knowledge of the structure of speech acoustics, capitalizing on large audio corpora and up-to-date statistical techniques (mostly based on sophisticated implementations of Hidden Markov Models, e.g. Schutz & Waibel, 2001, Yu & Deng, 2011). Data on speech rhythms, in relation with the syllabic structure, have been analyzed clearly in a number of works (Greenberg, 1999; Grant & Greenberg, 2003).

In spite of strong efforts in the field of audiovisual speech automatic recognition (Potamianos et al., 2003), characterization of the structure of audiovisual information is scarce. While an increasing number of papers on audiovisual speech perception presenting cognitive and neurophysiological data quote the “advance of the visual stream on the audio stream”, few papers provide quantitative evidence (see Chandrasekaran et al., 2009) and when they do, these are sometimes mistaken or oversimplified. Actually, the temporal relationship between visual and auditory information is far from constant from one situation to another (Troille et al., 2010). Concerning the perceptuo-motor link, the situation is even worse. Few systematic quantitative studies are available because of the difficulty to acquire articulatory data, and in these studies the focus is generally set on the so-called “inversion problem” (e.g. Ananthakrishnan & Engwall, 2011, Hueber et al., 2012) rather than a systematic characterization of the structure of the perceptuo-motor relationship. Finally, there is a strong lack of systematic investigations of the relationship between orofacial and bracchio-manual gestures in face-to-face communication.

We shall gather a large corpus of audio-visuo-articulatory-gestural speech. Articulatory data will be acquired through ultrasound, electromagnetic articulography (EMA) and video imaging. Labial configurations and estimates of jaw movements will be automatically extracted and processed thanks to a large range of video facial processing. We also additionally plan to record information about accompanying coverbal gestures by the hand and arm, thanks to an optotrack system enabling to track bracchio-manual gestures. A complete equipment for audio-video-ultrasound-EMA-optotrack acquisition and automatic processing, named ultraspeech-tools, is available in Grenoble (more information on www.ultraspeech.com). The corpus will consist in isolated syllables, chained syllables, simple sentences and read material. Elicitation paradigms will associate reading tasks (with material presented on a computer screen) and dialogic situations between the subject and an experimenter to evoke coverbal gestures as ecologically as possible.

The corpus will be analyzed, by extensive use and possibly development of original techniques, based on data–driven statistical models and machine learning algorithms, in the search for three major types of characteristics:

  1. Quantification of auditory, visual and motor rhythms, from kinematic data – e.g. acoustic envelope, lip height and/or width, variations in time of the principal components of the tongue deformations, analysis of the arm/hand/finger dynamics;

  2. Quantification of delays between sound, lips, tongue and hand in various kinds of configurations associated with coarticulation processes (e.g. vowel to vowel anticipatory and perseverative phenomena, consonant-vowel coproduction, vocal tract preparatory movement in silence) and oral/gestural coordination;

  3. Quantification of the amount of predictability between lips, tongue, hand and sound, through various techniques allowing the quantitative estimate of joint information (e.g. mutual information, entropy, co-inertia) and perform statistical inference between modalities (e.g. Graphical models such as dynamic Bayesian Framework, multi-stream HMM, etc.)

The work will be performed within a multidisciplinary group in GIPSA-Lab Grenoble, associating specialists in speech and gesture communication, cognitive processes, signal processing and machine learning (partners of the project: Jean-Luc Schwartz, Marion Dohen from the “Speech, Brain, Multimodality Development” team; Thomas Hueber, Laurent Girin from the “Talking Machines and Face to Face Interaction” team; Pierre-Olivier Amblard and Olivier Michel from the “Information in Complex Systems” team).



Practical information

The post-doc position is open for a two-year period, with a possible third-year prolongation. The position is open from September 2014, or slightly later if necessary.

Candidates should have a background in speech and signal processing, face-to-face communication, and machine learning, or at least two of these three domains.

Candidates should send as soon as possible a short email to Jean-Luc Schwartz (Jean-Luc.Schwartz@gipsa-lab.grenoble-inp.fr) to declare their intention to submit a full proposal.

Then they must send a full application file in the next weeks. This application file will include an extended CV and a list of publications, together with a letter explaining why they are interested in the project, what their specific interests could be, possibly suggesting other experiments related to the general question of the informational structure of audio-visuo-motor speech, and also how this position would fit into their future plans for the development of their own career. They should also provide two names (with email addresses) for recommendations about their applications. Preselected candidates will be interviewed.

 

Final selection should occur before mid-June.



Top

6-29(2014-03-30) Another Post-doc position in Grenoble (F)

Speech Unit(e)s

The multisensory-motor unity of speech

Understanding how speech unites the sensory and motor streams,

And how speech units emerge from perceptuo-motor interactions

 

ERC Advanced Grant, Jean-Luc Schwartz, GIPSA-Lab, Grenoble, France

 

 

Proposal for a post-doc position beginning in September 2014: “Joint development of perception, action and phonology”

 

Context

The Speech Unit(e)s project is focused on the speech unification process associating the auditory, visual and motor streams in the human brain, in an interdisciplinary approach combining cognitive psychology, neurosciences, phonetics (both descriptive and developmental) and computational models. The framework is provided by the “Perception-for-Action-Control Theory (PACT)” developed by the PI (Schwartz et al., 2012).

PACT is a perceptuo-motor theory of speech communication, which connects in a principled way perceptual shaping and motor procedural knowledge in speech multisensory processing. The communication unit in PACT is neither a sound nor a gesture but a perceptually shaped gesture, that is a perceptuo-motor unit. It is characterized by both articulatory coherence – provided by its gestural nature – and perceptual value – necessary for being functional. PACT considers two roles for the perceptuo-motor link in speech perception: online unification of the sensory and motor streams through audio-visuo-motor binding, and offline joint emergence of the perceptual and motor repertoires in speech development.



Objectives of the post-doc position

The general objective here is to gather phonetic data on the joint development of perception, action and phonology, to assess how perceptuo-motor speech units emerge and evolve in the course of acquisition, reacquisition, evolution or learning of a given phonological system.

Among the considerable amount of studies about the development of speech production and speech perception in the first years of life, very few consider the link between perception and action. Apart from historical disciplinary reasons – perceptual development is mainly studied by psycholinguists and production development by phoneticians – there is also a theoretical cause to this puzzling separation. Since it is now well known that phonetic perceptual abilities in infants are well in advance of production skills, it has become implicitly obvious for most researchers that perception was largely independent from production. The advance of perceptual on production skills has actually been considered as a major weakness of motor theories, and generally a decisive argument in favor of auditory theories of speech perception.

The view in PACT is different. While it is known that the construction of perceptual prototypes begins earlier than the development of motor prototypes, we assume in PACT that the later development of speech production intervenes in modifying the perceptual repertoire. This will be studied in this post-doc position through two series of experiments, aiming at illustrating two possible mechanisms for motor-driven evolution of perceptual phonetic categories.

  1. Reconfiguration of perceptual categories: coupled auditory and motor idiosyncrasies – The development of motor prototypes during acquisition should induce reconfiguration of perceptual categories. Therefore, motor idiosyncrasies – specific choices of individual ways to produce a target inside the space defined by native phonology – should result in perceptual idiosyncrasies: if a subject chooses to produce a specific phonological contrast in her language in a specific way, this should be mirrored in the way the subject perceives the same contrast. This hypothesis will be studied in various phonetic dimensions.

  2. Creation of new categories by perceptuo-motor coupling – According to PACT, the acquisition of new motor knowledge could enable the infant to create a new category. A typical example concerns plosive place of articulation, for which acoustic characterisation remains controversial (e.g. Stevens & Blumstein, 1981; Sussman et al., 1998), while articulatory characterization is straightforward. The relationship between the emergence of such categories in perception and in production is seldom considered. We assume that once an infant knows how to produce syllables with different places of articulation, she can realise that they are associated with specific articulatory gestures and hence form a new perceptual category related to articulatory properties. We will test this assumption in infants before and after the onset of canonical babbling (3 to 12 months), to possibly relate the emergence of perceptual categories with the onset of articulatory abilities. The same kind of studies will be possibly undertaken on pre-lingual children after cochlear implantation.

The work will be realized within a speech team in GIPSA-Lab Grenoble (partners in the project: Jean-Luc Schwartz, Anne Vilain), in close collaboration with a developmental and cognitive psychology team in LPNC Grenoble (partners in the project: Hélène Loevenbruck, Olivier Pascalis, David Meary).



Practical information

The post-doc position is open for a two-year period, with a possible third-year prolongation. The position is open from September 2014, or slightly later if necessary.

Candidates should have an experience in phonetics, cognitive and neurocognitive psychology, and developmental psychology, or at least two of these three domains.

Candidates should send as soon as possible a short email to Jean-Luc Schwartz (Jean-Luc.Schwartz@gipsa-lab.grenoble-inp.fr) to declare their intention to submit a full proposal.

Then they must send a full application file in the next weeks. This application file will include an extended CV and a list of publications, together with a letter explaining why they are interested in the project, what could be their specific interests, possibly proposing other experiments related to the general question of the joint development of perception, action and phonology; and also how this position would fit into their future plans for the development of their own career. They should also provide two names (with email addresses) for recommendations about their applications. Preselected candidates will be interviewed.

 

Final selection should occur before mid-June.

Top

6-30(2014-03-31) POSTDOCTORAL FELLOWSHIP in speech communication with robots for people with Alzheimer’s disease

--== POSTDOCTORAL FELLOWSHIP in speech communication with robots for people with Alzheimer’s disease ==--

 

Employer: Toronto Rehabilitation Institute and the University of Toronto

Title: PostDoc

Specialty: Machine learning, natural language processing, human-computer interaction

Location: Toronto Ontario Canada

Deadline: Until filled

Date Posted: 31 March, 2014

 

We are seeking a skilled postdoctoral fellow (PDF) whose expertise intersects automatic speech recognition (ASR) and human-computer interaction (HCI). The PDF will work with a team of internationally recognized researchers on software for two-way speech-based dialogue between individuals with Alzheimer’s disease (AD) and robot ‘caregivers’. This software will automatically adapt the vocabularies, language models, and acoustic models of the component ASR to data collected from individuals with AD. The type of speech produced by the robot in response to human activity is vital, and several statistical models of dialogue will be pursued, including partially-observable Markov decision processes.

 

Work will involve software development, data analysis, dissemination of results (e.g., papers and conferences), and partial supervision of graduate and undergraduate students. Some data collection may be involved. Although primarily a technological intervention, this work is highly multidisciplinary, with a strong connection to the field of speech-language pathology and clinical practice.

 

The successful applicant will have:

1)      A doctoral degree in a relevant field of computer science, electrical engineering, biomedical engineering, or a relevant discipline;

2)      Evidence of impact in research through a strong publication record in relevant venues;

3)      Evidence of strong collaborative skills, including possible supervision of junior researchers, students, or equivalent industrial experience;

4)      Excellent interpersonal, written, and oral communication skills;

5)      A strong technical background in machine learning, natural language processing, and human-computer interaction. Experience with clinical populations, especially those with dementia or Alzheimer’s disease, is preferred.

This work will be conducted at the Toronto Rehabilitation Institute and at the University of Toronto. Toronto Rehab has a diverse workforce and is an equal opportunity employer. Work can commence as soon as June 2014. The initial contract is for 1 year although extension is possible; the project itself will last 3 years.

 

Please contact Dr. Frank Rudzicz by email at frank@cs.toronto.edu with any questions or with 1) your up-to-date CV, 2) a cover letter, 3) a short 1-page statement of purpose if interested in applying to the position.

 

Top

6-31(2014-04-01) Ingénieur en Maths appliquées Kware, Aix en Provence (F)
Kware est une jeune entreprise innovante, spécialisée dans l'étude et l'extraction d'informations marketing. Dans le cadre de la finalisation de notre produit, nous recrutons un jeune docteur en informatique.

Poste : CDI ingénieur en recherche appliquée (H/F)

Diplôme : docteur en informatique (section 27)

Domaine : recherche d'informations, extraction d'informations, apprentissage automatique

Expérience : expérience industrielle souhaitée (thèse cifre), mais non requise, bonne expérience scientifique (publications nationales et internationales).

 

Missions :

L'ingénieur sera intégré au sein d'une équipe de 10 personnes.

 

Dans ce contexte, l’ingénieur se verra attribuer les missions suivantes :
Industrialisation des algorithmes,
Tests et évaluation,

Participation à l'intégration,

Profil : De formation Bac + 8 (titulaire d’un doctorat en informatique), spécialisé en traitement du langage, recherche d'informations ou extraction d'informations.

Vous êtes motivés par la recherche appliquée, l'industrialisation des algorithmes et la réalisation d'un produit industriel innovant.

Vous disposez dans l’idéal de connaissances complémentaires en méthodes d’apprentissage automatique.

Vos connaissances en programmation (JAVA) ainsi que vos qualités rédactionnelles seront vos atouts pour réussir dans vos missions.

Lieu : Aix en Provence

 

Candidature : adresser votre candidature par mail avec votre CV en
pièce jointe à frederic.duvert@kware.fr copie à michel.benoit@kware.fr avec pour sujet (impératif) :
[poste doc Kware] votre nom

Top

6-32(2014-04-08) New call for applicant/ research fellow, University of Macedonia, Greece

New call for applicant/ research fellow

The research group on hearing impairment and cochlear implants is located at the Dept. of

Educational and Social Policy of the University of Macedonia which works in collaboration

with the AHEPA Cochlear Implant Center as well as other local educational, speechpathology

and parental organizations in Greece. It focuses on assessing and optimizing

communication skills and also fostering educational success for children with hearing loss

and/or cochlear implants. Researchers have access to audiological and speech state-of-the

art equipment (nasometer, palatometer, OAE systems, etc) and work in a scientifically

focused and welcoming multidisciplinary environment. The doctoral students are enrolled in

the Graduate Program of the Dept. of Educational and Social Policy. A vacancy is available

for an:

Early Stage Researcher (PhD)

to investigate “Speech processing cues in children with hearing loss (CI)”

This position has been opened in the framework of ‘iCARE’, a European research and training

network (Marie Curie ITN) on ‘improving Children’s Auditory REhabilitation’. iCARE is an

international and interdisciplinary consortium from academia, industry and socio-economic

agencies. The position is available for 3 years, starting in June 2014 and aims in the

completion of a Ph.D. within 4 years. Limited funding may be available in the 4th year.

The aim of the ESR is to investigate the phono-prosodic cues that underlie the processing of

spoken words by profoundly hearing impaired children with cochlear implants (CI).

Objectives:

Assess the role of speech signal cues on lexical processing by CI children

Investigate the acquisition of phonological grammar by CI children in two languages,

Greek and another language.

Develop hierarchies of phono-prosodic cues that facilitate lexical processing

Develop e-learning/remote rehabilitation tools for clinical practice and/or parent

guidance.

Tasks and methodology:

Psycholinguistic experiments that involve presentation of controlled speech stimuli,

computerized, forced-choice tasks, reaction times and elicited productions.

Obtaining accuracy ratings and performing acoustic analysis of speech via spectrography.

Conducting speech and language assessments in young children with CI, working with

them in sound-attenuated rooms, making audio recordings.

Programming and carrying out computerized tasks.

Your profile:

A university Master degree (or equivalent) in Communication Disorders, Hearing

Impairment, Speech Science or Hearing Science

Scientific background in the study of speech, acoustics and phonology

A vested interest in hearing-impaired children and multi-disciplinary international team

work, demonstrated by willingness to move to Salonika, Greece.

Familiarity with research tools, such as PRAAT, E-Prime or other computerized software

for designing psycholinguistic tasks.

Technical competence for data analysis (Excell, SPSS, Statistica, etc.).

Excellent command of English language, both in academic writing and in verbal

communication. Knowledge of Greek is recommended.

Research experience in any of the above fields and clinical or other experience in working

with children is desirable.

How to apply? Please send your CV, full contact information for two references and letter of

intent to Prof. Areti Okalidou (okalidou@uom.gr). Make sure that you obtain a confirmation

response upon their receipt. Other documents such as English language proficiency and

recommendations may be requested to be available later on.

Mailing address:

Areti Okalidou,

Associate Professor,

Dept. of Educational and Social Policy,

University of Macedonia,

Egnatia 156, P.O. Box 1591,

Salonika 540 06

Greece.

Tel. : +30-2310-891358.

 

 

 

 

General Information:

Improving Children’s Auditory Rehabilitation (iCARE)

FP7‐Marie Curie Initial Training Network

Objectives

The objectives of improving Children’s Auditory REhabilitation (iCARE) are

1) to provide training to create a new generation of researchers capable of exploiting the

synergies between different disciplines to optimize spoken communication in children with

hearing impairment, and

2) to combine research across disciplines to develop novel methods, training skills and procedures

for improving auditory rehabilitation.

iCARE is an international and interdisciplinary consortium from academia, industry and

socio-economic agencies and offers a choice of 11 PhD and 3 postdoc positions, starting June or

July 2014. Each project is supervised by a multidisciplinary team of experts and will benefit from

extensive training. Please contact 1 or more partners for project specific educational

prerequisites. In December 2013 a website will be available with more details and a procedure for

applying.

Partners and topic

KU Leuven (Leuven, Belgium): Prof. Dr. Astrid van Wieringen

(astrid.vanwieringen@med.kuleuven.be) Temporal processing in children with unilateral

HI.

KU Leuven (Leuven, Belgium): Prof. dr .Wim Van Petegem

(wim.vanpetegem@kuleuven.be) Factors influencing e-learning.

RWTH (Aachen, Germany): Prof. Dr.-Ing. Janina Fels (Janina.Fels@akustik.rwth-aachen.de)

Acoustic Virtual Reality for HI and Development of ‘realistic’ test procedures for children

with HI.

LiU (Linköping, Sweden:) Prof. dr. Björn Lyxell (bjorn.lyxell@liu.se) Higher-order

(auditory-cognitive) remediation.

RUN (Nijmegen, the Netherlands): Prof. dr. Ad Snik (A.Snik@kno.umcn.nl) Optimizing

auditory scene analysis for the hearing impaired.

UCL (London, UK): dr. Lorna Halliday ( l.halliday@ucl.ac.uk) Auditory processing in

children with HI.

UOM (Thessaloniki, Greece): Prof. dr. Areti Okalidou (okalidou@uom.gr) Speech

processing cues in children with HI.

GAVLE (Gävle, Sweden): Prof. dr. Staffan Hygge (Staffan.Hygge@hig.se) Learning in

different acoustic scenes.

COCHLEAR UK (Mechelen, Belgium*): dr. Filiep Vanpoucke (fvanpoucke@cochlear.com)

Investigating listening situations by means of scene classifiers. Music remediation.

NOLDUS (Wageningen, the Netherlands): dr. Nico van der Aa (n.vanderaa@noldus.nl)

Development of a new system to determine quality of communication.

Eligibility

Marie Curie funding is intended to promote mobility of early career researchers within the

research community. Candidates must:

a) have received a degree (Bachelor or Master's) that qualifies them for PhD training,

b) should not have undertaken more than 4 years of fulltime research subsequent to that degree,

and

c) should not have been resident within the ‘country of interest’ (see individual projects) for more

than 12 months within the 3 years prior to 1 June 2014.

For a full description of the eligibility conditions see:

http://ec.europa.eu/research/mariecurieactions/

An excellent 1st degree, good verbal and written communication skills in English, and an interest

in multidisciplinary research are essential.

At this stage applicants can express their interest and/or ask for additional information by

contacting the individual partner(s). Mobility expenses are provided in addition to a salary.

Prof dr Astrid van Wieringen ExpORL,

Dept Neurosciences Herestraat 49, 3000 Leuven, Belgium

astrid.vanwieringen@med.kuleuven.be

tel 00 32 16 330478

 

Top

6-33(2014-04-10) PhD thesis: Smart dialogue based on human-human conversation, Orange, Issy-les-Moulineaux, F

PhD thesis: Smart dialogue based on human-human conversation

 

Supervisor: Laroche Romain (romain.laroche@orange.com)

Company: Orange Labs (www.orange.com/en/innovation)

Place: Issy-les-Moulineaux (Paris, France)

To start around October 2014

 

  • Context

Automatic Speech Recognition is a module that transcribes speech to text. Its robustness, accurateness, and universality have greatly improved these last years, so that it is now possible to use it with a generic language model, even in a noisy environment. This technologic advance pushes numerous innovations, including the one tackled by this PhD thesis: active listening to a human-human conversation to extract meaning and deliver a contextual service related to this meaning.

 

Internally to Orange Labs, we have already worked a service of this kind in the contextualisation service that is integrated in the work environment of call user agents. This environment embeds several professional services: chat, e-mail, call management, appointment scheduling, location, Customer Relationship Management, scripting, statistics, etc. The contextualisation tool consists in guiding the agent by launching semi-automatically or fully-automatically applications according to conversational patterns detected during communication.

 

As well, a personal assistant named MindMeld (http://www.expectlabs.com/mindmeld/) has been commercialised. It listens to phone calls and proposes in real time contents related to approached subjects.

 

The PhD thesis subject will focus on the dialogical part, namely from one side, not only recognize the keywords or even analyze sentences, but placing analysis in a human-human dialogue model ; and from the other side, not only display an information or propose an action, but start a dialogue with the user. Both fields have never been investigated at this time to our knowledge.

 

The scientific domain of the PhD thesis will be split into semantic analysis of human-human dialogue and human-machine dialogue systems. The latter include interactive voice response systems, but also chatbots or interactions that some video games propose between the player and some characters. Spoken dialogue systems are expanding and deal commercially several billions calls a year.

 

  • NADIA team

We are a small unit of 8 permanents, 3 PhD students, and a post doctorate researcher. The team is in charge of Orange dialogue technology: Disserto suite. Disserto has been used to develop dozens of interactive voice response systems, which receive more than 100M calls a year. Some Disserto-based multimodal prototypes have been released in the research side as well. In addition to its strong industrial implication, NADIA is also involved in academic research with 3 conference articles published in 2013 and already 4 accepted in 2014.

 

  • Scientific objectives

PhD thesis scientific thematic revolves around three main disjointed subjects:

  • How to model semantic analysis of a human-human conversation and extract a meaning further used in an application?

  • How to initiate, lead and conclude a dialogue with a user that is already committed in a conversation with someone else?

  • How to make this kind of listening and dialoguing application easily extensible, and even customizable?

 

We will ask to the PhD student to endorse the prototype development of several demonstrators and to organise experimentation campaigns to evaluate the results of her/his work.

 

On the other hand, the following subjects are beyond the scope of the PhD: automatic speech recognition (we will use a plug and play product) and multimodality theoretic studies. Both are very large fields of research that must be studied separately.

 

  • specialities,

  • Spoken Dialogue Systems

  • Human-human dialogue theory

  • Natural Language Processing

  • Machine Learning

 

  • Required educational level,

  • Research master of science or « école d’ingénieur »

  • At least one of the cited specialities recorded inside the university curriculum

 

  • Required experience,

At least an internship in one of the cited specialities, or more largely in Artificial Intelligence

 

 

  • Attractiveness of the position

This PhD thesis offers the opportunity to contribute to the future of dialogue applications, and to participate to putting them to everyone’s reach in everyday life. Those two domains are currently fast-growing and their emergence seems ineluctable in the ten years to come. According to Gartner, personal assistants are among the top10 technological trends for 2014, inside the “smart machines” thematic.

 

The PhD student is integrated in a small team comprising three other PhD students and a post-doctorate researcher. All team works in the dialogue system field. The other Orange Labs teams gather every kind of artificial intelligence skills and more largely in computer science. It is the perfect environment to lead significant research and get quick and high level advice from experts.

 

Orange warrants that the PhD student will work in the best conditions by making several commitments:

  • Provision of a state-of-the-art industrial software: our historical tool, namely Disserto, will be used by the PhD student. It will enable her/him to tackle the PhD issues without spending to much effort on peripheral development.

  • Provision of our previous research results: research and market watch, theoretical studies and code will be made available. Orange Labs gather 3700 researchers. Whatever the research study is, it is likely that somebody has prepared the ground.

  • Provision of necessary equipment: to study dialogue in home environment, we have already invested on equipment to build a showroom.

  • Experimentation programs: we are used at Orange Labs to launch user test campaigns on our internal development. Each campaign is specific, but to give an idea, my first PhD student launched three experimentations with 500 unique testers (and almost 2000 dialogues)

Provision of data: Orange has a big experience in spoken dialogue systems and has a large amount of data available (Disserto-based systems receive more than 150M calls a year).

 

 

 

 

Top

6-34(2014-04-08) PhD analyse video/texte à Aix-Marseille (F)

Dans le cadre d'un co-financement entre la DGA et l'Université d'Aix Marseille, nous recherchons des candidats pour un contrat doctoral de 3 ans, débutant en septembre 2014, portant sur l'analyse automatique de documents vidéo, et plus particulièrement sur des approches multimodales de traitement de l'information visuelle, audio et texte.

Nous recherchons des candidats titulaire d'un Master Informatique (ou équivalent), ou en cours d'obtention d'un tel Master (et qui sont actuellement en stage).

La date limite de candidature est fixée au 25 avril 2014. Le dossier de candidature est composé d'un CV détaillé, la copie du dernier diplôme ou de l'attestation de réussite avec un relevé de notes et tous les éléments que vous jugerez utiles de joindre pour conforter votre dossier de candidature.

Le titre de la proposition de thèse est : 'Compréhension Multimodale – vers des traitements joints audio/image pour la compréhension multimodale de documents vidéo'
Mots-clés : traitement automatique de la parole, traitement automatique de la langue, traitement d'image, apprentissage automatique, recherche d'information.
Une description du sujet est disponible à l'adresse suivante : http://pageperso.lif.univ-mrs.fr/~frederic.bechet/prop_these_court_DGA2014_LIF_TALEP.pdf

Pour toute demande de renseignement : frederic.bechet@univ-amu.fr

Top



 Organisation  Events   Membership   Help 
 > Board  > Interspeech  > Join - renew  > Sitemap
 > Legal documents  > Workshops  > Membership directory  > Contact
 > Logos      > FAQ
       > Privacy policy

© Copyright 2024 - ISCA International Speech Communication Association - All right reserved.

Powered by ISCA