Foundations and Trends in Signal Processing (www.nowpublishers.com/sig) has published the following issue:   

Volume 7, Issue 3-4                                                                                                                                                                   
Deep Learning: Methods and Applications                                                               
By Li Deng and Dong Yu (Microsoft Research, USA)       
http://dx.doi.org/10.1561/2000000039                                       

Top

Tackling the Complexity in Speech

The present volume is meant to give the reader an impression of the range of questions and topics that are currently subject of international research in the discovery of complexity, the organization of complexity, and the modelling of complexity. These are the main sections of our volume. Each section includes four carefully selected chapters. They deal with facets of speech production, speech acoustics, and/or speech perception or recognition, place them in an integrated phonetic-phonological perspective, and relate them in more or less explicit ways to aspects of speech technology. Therefore, we hope that this volume can help speech scientists with traditional training in phonetics and phonology to keep up with the latest developments in speech technology. In the opposite direction, speech researchers starting from a technological perspective will hopefully get inspired by reading about the questions, phenomena, and communicative functions that are currently addressed in phonetics and phonology. Either way, the future of speech research lies in international, interdisciplinary collaborations, and our volume is meant to reflect and facilitate such collaborations.

https://e-shop.ff.cuni.cz/books/monographs_eng/opera_facultatis_philosophicae_eng/tackling_the_complexity_in_spee_-1153

Top

 'Robust Automatic Speech Recognition'

• The  first book that provides a comprehensive review on noise and reverberation robust speech recognition methods in the era of deep neural networks
• Connects robust speech recognition techniques to machine learning paradigms with rigorous mathematical treatment
• Provides elegant and structural ways to categorize and analyze noise-robust speech recognition techniques
• Written by leading researchers who have been actively working on the subject matter in both industrial and academic organizations for many years

https://na01.safelinks.protection.outlook.com/?url=http%3a%2f%2fstore.elsevier.com%2fRobust-Automatic-Speech-Recognition%2fJinyu-Li%2fisbn-9780128023983%2f.&data=01%7c01%7cygong%40exchange.microsoft.com%7c3bd27ec380c8427e97e208d2975aca2a%7c72f988bf86f141af91ab2d7cd011db47%7c1&sdata=PRRo3i4DYNV1rNmVlhPMaHa0pUN4oi%2b1khyjctDXxjU%3d

Top

Barbosa, P. A. and Madureira, S. Manual de Fonética Acústica Experimental. Aplicações a dados do português. 591 p. São Paulo: Cortez, 2015. [In Portuguese]     


http://www.cortezeditora.com.br/manual-de-fonetica-acustica-experimental-1599.aspx/p

This manual of Experimental Acoustic Phonetics is conceived for Undergraduate and Graduate classes on areas such as Acoustic Phonetics, Phonology, Communications Engineering, Music, Acoustic Physics, Speech Theraphy, among others.  Starting with a theoretical and methodological presentation of Acoustic Phonetics Theory and Techniques in five chapters,  including a chapter on experimental methods, the book follows with detailed acoustic analysis of all classes of sounds using audio files from both European and Brazilian Portuguese as data.
All analyses are explained step by step using Praat. The audiofiles are available on the book web site and can be downloaded.  All techniques can be applied to any language, of course. Proposed exercices at the end of each chapter allow the teacher o evaluate the student progress.

Top

Les entités nommées pour le traitement automatique des langues

Damien Nouvel, Inalco, Maud Ehrmann, EPFL
Sophie Rosset, CNRS  

Top

R.Fuchs,  'Speech Rhythm in Varieties of English' has appeared with Springer, in the 'Prosody, Phonology and Phonetics' series: https://www.springer.com/gp/book/9783662478172

Top

Phase-Aware Signal Processing in Speech Communication: Theory and Practice

Pejman Mowlaee, Johannes Stahl, Josef Kulmer, Florian Mayer

http://eu.wiley.com/WileyCDA/WileyTitle/productCd-1119238811.html

Top

Appen ButlerHill 

A global leader in linguistic technology solutions

RECENT CATALOG ADDITIONS—MARCH 2012

1. Speech Databases

1.1 Telephony

2. Pronunciation Lexica

Appen Butler Hill has considerable experience in providing a variety of lexicon types. These include:

 Pronunciation Lexica providing phonemic representation, syllabification, and stress (primary and secondary as appropriate)

 Part-of-speech tagged Lexica providing grammatical and semantic labels

 Other reference text based materials including spelling/mis-spelling lists, spell-check dictionar-ies, mappings of colloquial language to standard forms, orthographic normalization lists.

Over a period of 15 years, Appen Butler Hill has generated a significant volume of licensable material for a wide range of languages. For holdings information in a given language or to discuss any customized development efforts, please contact: sales@appenbutlerhill.com

4. Other Language Resources

 Morphological Analyzers – Farsi/Persian & Urdu

 Arabic Thesaurus

 Language Analysis Documentation – multiple languages

For additional information on these resources, please contact: sales@appenbutlerhill.com

5. Customized Requests and Package Configurations

Appen Butler Hill is committed to providing a low risk, high quality, reliable solution and has worked in 130+ languages to-date supporting both large global corporations and Government organizations.

We would be glad to discuss to any customized requests or package configurations and prepare a cus-tomized proposal to meet your needs.

                                                         www.appenbutlerhill.com

Top

We are happy to announce the release of DEMAND, a set of real-world
16-channel noise recordings designed for the evaluation of microphone
array processing techniques.

http://www.irisa.fr/metiss/DEMAND/

1.5 h of noise data were recorded in 18 different indoor and outdoor
environments and are available under the terms of the Creative Commons Attribution-ShareAlike License.

Joachim Thiemann (CNRS - IRISA)
Nobutaka Ito (University of Tokyo)
Emmanuel Vincent (Inria Nancy - Grand Est)

Top

Aide à la finalisation de corpus oraux ou multimodaux pour diffusion, valorisation et dépôt pérenne

Le consortium IRCOM de la TGIR Corpus et l’EquipEx ORTOLANG s’associent pour proposer une aide technique et financière à la finalisation de corpus de données orales ou multimodales à des fins de diffusion et pérennisation par l’intermédiaire de l’EquipEx ORTOLANG. Cet appel ne concerne pas la création de nouveaux corpus mais la finalisation de corpus existants et non-disponibles de manière électronique. Par finalisation, nous entendons le dépôt auprès d’un entrepôt numérique public, et l’entrée dans un circuit d’archivage pérenne. De cette façon, les données de parole qui ont été enrichies par vos recherches vont pouvoir être réutilisées, citées et enrichies à leur tour de manière cumulative pour permettre le développement de nouvelles connaissances, selon les conditions d’utilisation que vous choisirez (sélection de licences d’utilisation correspondant à chacun des corpus déposés).

Cet appel d’offre est soumis à plusieurs conditions (voir ci-dessous) et l’aide financière par projet est limitée à 3000 euros. Les demandes seront traitées dans l’ordre où elles seront reçues par l’ IRCOM. Les demandes émanant d’EA ou de petites équipes ne disposant pas de support technique « corpus » seront traitées prioritairement. Les demandes sont à déposer du 1^er septembre 2013 au 31 octobre 2013. La décision de financement relèvera du comité de pilotage d’IRCOM. Les demandes non traitées en 2013 sont susceptibles de l’être en 2014. Si vous avez des doutes quant à l’éligibilité de votre projet, n’hésitez pas à nous contacter pour que nous puissions étudier votre demande et adapter nos offres futures.

Pour palier la grande disparité dans les niveaux de compétences informatiques des personnes et groupes de travail produisant des corpus, L’ IRCOM propose une aide personnalisée à la finalisation de corpus. Celle-ci sera réalisée par un ingénieur IRCOM en fonction des demandes formulées et adaptées aux types de besoin, qu’ils soient techniques ou financiers.

Les conditions nécessaires pour proposer un corpus à finaliser et obtenir une aide d’IRCOM sont :

• Pouvoir prendre toutes décisions concernant l’utilisation et la diffusion du corpus (propriété intellectuelle en particulier).

• Disposer de toutes les informations concernant les sources des corpus et le consentement des personnes enregistrées ou filmées.

• Accorder un droit d’utilisation libre des données ou au minimum un accès libre pour la recherche scientifique.

Les demandes peuvent concerner tout type de traitement : traitements de corpus quasi-finalisés (conversion, anonymisation), alignement de corpus déjà transcrits, conversion depuis des formats « traitement de textes », digitalisation de support ancien. Pour toute demande exigeant une intervention manuelle importante, les demandeurs devront s’investir en moyens humains ou financiers à la hauteur des moyens fournis par IRCOM et ORTOLANG.

IRCOM est conscient du caractère exceptionnel et exploratoire de cette démarche. Il convient également de rappeler que ce financement est réservé aux corpus déjà largement constitués et ne peuvent intervenir sur des créations ex-nihilo. Pour ces raisons de limitation de moyens, les propositions de corpus les plus avancés dans leur réalisation pourront être traitées en priorité, en accord avec le CP d’IRCOM. Il n’y a toutefois pas de limite « théorique » aux demandes pouvant être faites, IRCOM ayant la possibilité de rediriger les demandes qui ne relèvent pas de ses compétences vers d’autres interlocuteurs.

Les propositions de réponse à cet appel d’offre sont à envoyer à ircom.appel.corpus@gmail.com. Les propositions doivent utiliser le formulaire de deux pages figurant ci-dessous. Dans tous les cas, une réponse personnalisée sera renvoyée par IRCOM.

Ces propositions doivent présenter les corpus proposés, les données sur les droits d’utilisation et de propriétés et sur la nature des formats ou support utilisés.

Cet appel est organisé sous la responsabilité d’IRCOM avec la participation financière conjointe de IRCOM et l’EquipEx ORTOLANG.

Pour toute information complémentaire, nous rappelons que le site web de l'Ircom (http://ircom.corpus-ir.fr) est ouvert et propose des ressources à la communauté : glossaire, inventaire des unités et des corpus, ressources logicielles (tutoriaux, comparatifs, outils de conversion), activités des groupes de travail, actualités des formations, ...

L'IRCOM invite les unités à inventorier leur corpus oraux et multimodaux - 70 projets déjà recensés - pour avoir une meilleure visibilité des ressources déjà disponibles même si elles ne sont pas toutes finalisées.

Le comité de pilotage IRCOM

Utiliser ce formulaire pour répondre à l’appel : Merci.

Réponse à l’appel à la finalisation de corpus oral ou multimodal

Nom du corpus :

Nom de la personne à contacter :

Adresse email :

Numéro de téléphone :

Nature des données de corpus :

Existe-t’il des enregistrements :

Quel média ? Audio, vidéo, autre…

Quelle est la longueur totale des enregistrements ? Nombre de cassettes, nombre d’heures, etc.

Quel type de support ?

Quel format (si connu) ?

Existe-t’il des transcriptions :

Quel format ? (papier, traitement de texte, logiciel de transcription)

Quelle quantité (en heures, nombre de mots, ou nombre de transcriptions) ?

Disposez vous de métadonnées (présentation des droits d’auteurs et d’usage) ?

Disposez-vous d’une description précise des personnes enregistrées ?

Disposez-vous d’une attestation de consentement éclairé pour les personnes ayant été enregistrées ? En quelle année (environ) les enregistrements ont eu lieu ?

Quelle est la langue des enregistrements ?

Le corpus comprend-il des enregistrements d’enfants ou de personnes ayant un trouble du langage ou une pathologie ?

Si oui, de quelle population s’agit-il ?

Dans un souci d’efficacité et pour vous conseiller dans les meilleurs délais, il nous faut disposer d’exemples des transcriptions ou des enregistrements en votre possession. Nous vous contacterons à ce sujet, mais vous pouvez d’ores et déjà nous adresser par courrier électronique un exemple des données dont vous disposez (transcriptions, métadonnées, adresse de page web contenant les enregistrements).

Nous vous remercions par avance de l’intérêt que vous porterez à notre proposition. Pour toutes informations complémentaires veuillez contacter Martine Toda martine.toda@ling.cnrs.fr ou à ircom.appel.corpus@gmail.com.

Top

Rhapsodie: un Treebank prosodique et syntaxique de français parlé

Nous avons le plaisir d'annoncer que la ressource Rhapsodie, Corpus de français parlé annoté pour la prosodie et la syntaxe, est désormais disponible sur http://www.projet-rhapsodie.fr/

Le treebank Rhapsodie est composé de 57 échantillons sonores (5 minutes en moyenne, au total 3h de parole, 33000 mots) dotés d’une transcription orthographique et phonétique alignées au son.

Il s'agit d’une ressource de français parlé multi genres (parole privée et publique ; monologues et dialogues ; entretiens en face à face vs radiodiffusion, parole plus ou moins interactive et plus ou moins planifiée, séquences descriptives, argumentatives, oratoires et procédurales) articulée autour de sources externes (enregistrements extraits de projets antérieurs, en accord avec les concepteurs initiaux) et internes. Nous tenons en particulier à remercier les responsables des projets CFPP2000, PFC, ESLO, C-Prom ainsi que Mathieu Avanzi, Anne Lacheret, Piet Mertens et Nicolas Obin.

Les échantillons sonores (wave & MP3, pitch nettoyé et lissé), les transcriptions orthographiques (txt), les annotations macrosyntaxiques (txt), les annotations prosodiques (xml, textgrid) ainsi que les metadonnées (xml & html) sont téléchargeables librement selon les termes de la licence Creative Commons Attribution - Pas d’utilisation commerciale - Partage dans les mêmes conditions 3.0 France.

Les annotations microsyntaxiques seront disponibles prochainement

 Les métadonnées sont également explorables en ligne grâce à un browser.

 Les tutoriels pour la transcription, les annotations et les requêtes sont disponibles sur le site Rhapsodie.

 Enfin, L’annotation prosodique est interrogeable en ligne grâce au langage de requêtes Rhapsodie QL.

 L'équipe Ressource Rhapsodie (Modyco, Université Paris Ouest Nanterre)

Sylvain Kahane, Anne Lacheret, Paola Pietrandrea, Atanas Tchobanov, Arthur Truong.

 Partenaires : IRCAM (Paris), LATTICE (Paris), LPL (Aix-en-Provence), CLLE-ERSS (Toulouse).

********************************************************

Rhapsodie: a Prosodic and Syntactic Treebank for Spoken French

We are pleased to announce that Rhapsodie, a syntactic and prosodic treebank of spoken French created with the aim of modeling the interface between prosody, syntax and discourse in spoken French is now available at   http://www.projet-rhapsodie.fr/

The Rhapsodie treebank is made up of 57 short samples of spoken French (5 minutes long on average, amounting to 3 hours of speech and a 33 000 word corpus) endowed with an orthographical phoneme-aligned transcription . 

The corpus is representative of different genres (private and public speech; monologues and dialogues; face-to-face interviews and broadcasts; more or less interactive discourse; descriptive, argumentative and procedural samples, variations in planning type).

The corpus samples have been mainly drawn from existing corpora of spoken French and partially created within the frame of theRhapsodie project. We would especially like to thank the coordinators of the  CFPP2000, PFC, ESLO, C-Prom projects as well as Piet Mertens, Mathieu Avanzi, Anne Lacheret and Nicolas Obin.

The sound samples (waves, MP3, cleaned and stylized pitch), the orthographic transcriptions (txt), the macrosyntactic annotations (txt), the prosodic annotations  (xml, textgrid) as well as the metadata (xml and html) can be freely downloaded under the terms of the Creative Commons licence Attribution - Noncommercial - Share Alike 3.0 France.

Microsyntactic annotation will be available soon.

The metadata are  searchable on line through a browser.

The prosodic annotation can be explored on line through the Rhapsodie Query Language.

The tutorials of transcription, annotations and Rhapsodie Query Language  are available on the site.

The Rhapsodie team (Modyco, Université Paris Ouest Nanterre :

Sylvain Kahane, Anne Lacheret, Paola Pietrandrea, Atanas Tchobanov, Arthur Truong.

Partners: IRCAM (Paris), LATTICE (Paris), LPL (Aix-en-Provence),CLLE-ERSS (Toulouse).

Top

We have created and made publicly available a dense audio-visual person-oriented ground-truth annotation of a feature movie (100 minutes long): “Hannah and her sisters” by Woody Allen.

The annotation includes

•          Face tracks in video (densely annotated, i.e., in each frame, and person-labeled)

•             Speech segments in audio (person-labeled)

•             Shot boundaries in video



The annotation can be useful for evaluating



•   Person-oriented video-based tasks (e.g., face tracking, automatic character naming, etc.)

•             Person-oriented audio-based tasks (e.g., speaker diarization or recognition)

•             Person-oriented multimodal-based tasks (e.g., audio-visual character naming)



Detail on Hannah dataset and access to it can be obtained there:

https://research.technicolor.com/rennes/hannah-home/

https://research.technicolor.com/rennes/hannah-download/



Acknowledgments:

This work is supported by AXES EU project: http://www.axes-project.eu/










Alexey Ozerov Alexey.Ozerov@technicolor.com

Jean-Ronan Vigouroux,

Louis Chevallier

Patrick Pérez

Technicolor Research & Innovation



 

Top

Text to         Speech Synthesis:
      over an hour of speech       synthesis samples from         1968 to 2001 by       25 French, Canadian, US , Belgian,       Swedish, Swiss systems
     
      33 ans de synthèse de la parole à         partir du texte: une promenade sonore (1968-2001)
        (33 years of Text to Speech Synthesis       in French : an audio tour (1968-2001)       )
      Christophe d'Alessandro
      Article published in         Volume 42 - No. 1/2001 issue of  Traitement       Automatique des Langues  (TAL,       Editions Hermes),         pp. 297-321.
     
      posted to:
      http://groupeaa.limsi.fr/corpus:synthese:start

Top

Press Release - Immediate - Paris, France, December 13, 2013

Establishing the International Standard Language Resource Number (ISLRN)

12 major NLP organisations announce the establishment of the ISLRN, a Persistent Unique Identifier, to be assigned to each Language Resource.

On November 18, 2013, 12 NLP organisations have agreed to announce the establishment of the International Standard Language Resource Number (ISLRN), a Persistent Unique Identifier, to be assigned to each Language Resource. Experiment replicability, an essential feature of scientific work, would be enhanced by such unique identifier. Set up by ELRA, LDC and AFNLP/Oriental-COCOSDA, the ISLRN Portal will provide unique identifiers using a standardised nomenclature, as a service free of charge for all Language Resource providers. It will be supervised by a steering committee composed of representatives of participating organisations and enlarged whenever necessary.

More information on ELRA and the ISLRN, please contact: Khalid Choukri choukri@elda.org

More information on ELDA, please contact: Hélène Mazo mazo@elda.org

ELRA

55-57, rue Brillat Savarin

75013 Paris (France)

Tel.: +33 1 43 13 33 33

Fax: +33 1 43 13 33 30

Top

Further to the establishment of the International Standard Language Resource Number (ISLRN) as a unique and universal identification schema for Language Resources on November 18, 2013, ELRA, LDC and AFNLP/Oriental-COCOSDA now announce the opening of the ISLRN Portal (www.islrn.org). As a service free of charge for all Language Resource providers and under the supervision of a steering committee composed of representatives of participating organisations, the ISLRN Portal provides unique identifiers using a standardised nomenclature.

Overview
The 13-digit ISLRN format is: XXX-XXX-XXX-XXX-X. It can be allocated to any Language Resource; its composition is neutral and does not include any semantics in reference to the type or nature of the Language Resource. The ISLRN is a randomly created number with a check digit that validates a Verhoeff algorithm.

Two types of external players may interact with the ISLRN Portal: Visitors and Providers. Visitors may browse the web site and search for the ISLRN of a given Language Resource by its name or by its number if it exists. Providers are registered and own credentials. They can request a new ISLRN for a given Language Resource. A provider has the possibility to become certified, after moderation, in order to be able to import metadata in XML format.

The functionalities that can be accessed by Visitors are:

-          Identify a language resource according to its ISLRN
-          Identify an ISLRN by the name of a language resource
-          Get information about ISLRN, FAQ, Basic Metadata, Legal Information
-          View last 5 accepted resources (“What’s new” block on home page)
-          Sign up to become a provider

The functionalities that can be accessed by Providers, once they have signed up, are:

-          Log in
-          Request an ISLRN according to the metadata of a given resource
-          Request to become a certified provider so as to import XML files containing metadata
-          Import one or more metadata descriptions in XML to request ISLRN(s) (only for certified providers)
-          Edit pending requests
-          Access previous requests
-          Contact a Moderator or an Administrator
-          Edit Providers’ own profile

ISLRN request is handled by moderators within 5 working days.
Contact: islrn@elda.org

Background
The International Standard Language Resource Number (ISLRN) is a unique and universal identification schema for Language Resources which provides Language Resources with unique identifier using a standardised nomenclature. It also ensures that Language Resources are correctly identified, and consequently, recognised with proper references for their usage in applications in R&D projects, products evaluation and benchmark as well as in documents and scientific papers. Moreover, it is a major step in the interconnected world that Human Language Technologies (HLT) has become: unique resources must be identified as they are and meta-catalogues need a common identification format to manage data correctly.

The ISLRN does not intend to replace local and specific identifiers, it is not meant to be a legal deposit, not an obligation, but rather an essential and best practice. For instance a resource that is distributed by several data centres will still have the “local” data-centre identifier but will have a unique ISLRN.

********************************************************************
About ELRA
The European Language Resources Association (ELRA) is a non-profit making organisation founded by the European Commission in 1995, with the mission of providing a clearing house for language resources and promoting Human Language Technologies (HLT). To find out more about ELRA, please visit www.elra.info.

About LDC
Founded in 1992, the Linguistic Data Consortium (LDC) is an open consortium of universities, companies and government research laboratories. It creates, collects and distributes speech and text databases, lexicons, and other resources for research and development purposes. The University of Pennsylvania is the LDC's host institution. To find out more about LDC, please visit www.ldc.upenn.edu.

About AFNLP
The mission of the Asian Federation of Natural Language Processing (AFNLP) is to promote and enhance R&D relating to the computational analysis and the automatic processing of all languages of importance to the Asian region by assisting and supporting like-minded organizations and institutions through information sharing, conference organization, research and publication co-ordination, and other forms of support. To find out more about AFNLP, please visit www.afnlp.org.

About Oriental-COCOSDA
The International Committee for the Co-ordination and Standardisation of Speech Databases and Assesment Techniques, Oriental-COCOSDA, has been established to encourage and promote international interaction and cooperation in the foundation areas of Spoken Language Processing, especially for Speech Input/Output. To find out more about Oriental-COCOSDA, please visit our web site: www.cocosda.org

Top

Speechocean – update (Jan 2017):

Speechocean: A global language resources and data services supplier

About Speechocean

Speechocean is one of the world well-known language related resources & services provider in the fields of Human Computer Interaction and Human Language Technology. At present, we can provide data services with 110+ languages and dialects across the world.

KingLine Data Center ---Data Sharing Platform

Kingline Data Center is operated and supervised by Speechocean, which is mainly focused on language resources creating and providing for research and development of human language technology.

These diversified corpora are widely used for the research and development in the fields of Speech Recognition, Speech Synthesis, Natural Language Processing, Machine Translation, Web Search, etc. All corpora are openly accessible for users all over the world, including users from scientific research institutions, enterprises or individuals.

For more detailed information, please visit our website: http://kingline.speechocean.com

New released corpora:

1. Uighur Speech Recognition Corpus-Sentence/Conversation (Telephone)-300 Speakers

ID: King-ASR-450

The Uighur Telephone Speech Recognition Corpus was collected in China. It contains the voices of 300 different speakers (150 males, 150 females) who were balanced distributed in age (mainly 18-35, 36-45, >46), gender and regional accents (for the details, please see the technical document). The script contains 120,000(approx.) utterances in total (for more details of script structure design, please check the specification), specially designed to provide materials for both training and testing of many classes of speech recognizers. Each speaker was recorded in quiet environments (home/office). Telephone platform, i.e. IVR was used for speech collection. Each utterance wave was stored in a separate file and uncompressed. A pronunciation lexicon is available. All audio files were manually transcribed and annotated by native transcribers. Details are available with specification.

2. Hindi Speech Recognition Corpus- Conversation (Mobile)- 200 Speakers

ID: King-ASR-323

The Hindi Mobile Speech Recognition Corpus was collected in India. It contains the voices of 200 different speakers (108 males, 92 females) who were balanced distributed in age (16-30, 31-45, 46-60), gender and regional accents (for the details, please see the technical document). More than 20 topics were included in total (for more details of script structure design, please check the specification), specially designed to provide materials for both training and testing of many classes of speech recognizers. Each speaker was recorded in a quiet office environment. Mobile platforms, i.e. iOS, Android and Windows were used for speech collection. Each utterance wave was stored in a separate file and uncompressed. A pronunciation lexicon is available with a phonemic transcription in SAMPA. All manually checked. All audio files were manually transcribed and annotated by native transcribers. Details are available with specification.

3. Kids Mandarin Speech Recognition Corpus-Sentence (Mobile, Desktop & Smart TV)-575 Speakers

ID: King-ASR-409

The Kids Mandarin Speech Recognition Corpus was collected in China Liaoning Province and Hebei Province. It contains the voices of 575 different native speakers (283 males, 292 females) who were balanced distributed in age (4-9 years old), gender and regional accents (for the details, please see the technical document). The script contains 396,000(approx.) utterances in total( for more details of script structure design, please check the specification), specially designed to provide material for both training and testing of many classes of speech recognizers. Each speaker was recorded in a quiet office room. Mobile phone, desktop and smart TV were used for speech collection. Each utterance wave is stored in a separate file and uncompressed. A pronunciation lexicon is available with a phonemic transcription in Pinyin. All manually checked. All audio files were manually transcribed and annotated by native transcribers. Details are available with specification.

4. Hong Kong English Speech Recognition Corpus-Sentence (Mobile)-200 Speakers

ID: King-ASR-287

The Hong Kong English Mobile Speech Recognition Corpus was collected in Hong Kong. It contains the voices of 200 different speakers (99 males, 101 females) who were balanced distributed in age (18-30, 31-45, 46-60), gender and regional accents (for the details, please see the technical document). The script contains 179,406(approx.) utterances in total (for more details of script structure design, please check the specification), specially designed to provide materials for both training and testing of many classes of speech recognizers. Each speaker was recorded in a quiet environment. Mobile platforms, i.e. iOSAndroidWindows were used for speech collection. Each utterance wave was stored in a separate file and uncompressed. A pronunciation lexicon is available with a phonemic transcription in Hepburn. All manually checked. All audio files were manually transcribed and annotated by native transcribers. Details are available with specification.

Contact Information

Xianfeng Cheng

VP

Tel: +86-10-62660928; +86-10-62660053 ext.8080

Mobile: +86 13681432590

Skype: xianfeng.cheng1

Email: chengxianfeng@speechocean.com; cxfxy0cxfxy0@gmail.com

Website: www.speechocean.com

Top

kidLUCID: London UCL Children’s Clear Speech in Interaction Database

We are delighted to announce the availability of a new corpus of spontaneous speech for children aged 9 to 14 years inclusive, produced as part of the ESRC-funded project on ‘Speaker-controlled Variability in Children's Speech in Interaction’ (PI: Valerie Hazan).

Speech recordings (a total of 288 conversations) are available for 96 child participants (46M, 50F, range 9;0 to 15;0 years), all native southern British English speakers. Participants were recorded in pairs while completing the diapix spot-the-difference picture task in which the pair verbally compared two scenes, only one of which was visible to each talker. High-quality digital recordings were made in sound-treated rooms. For each conversation, a stereo audio recording is provided with each speaker on a separate channel together with a Praat Textgrid containing separate word- and phoneme-level segmentations for each speaker.

There are six recordings per speaker pair made in the following conditions:

• NOB (No barrier): both speakers heard each other normally

• VOC (Vocoder): one conversational partner heard the other's speech after it had been processed in real time through a noise-excited three channel vocoder

• BAB (Babble): one conversational partner heard the other's speech in a background of adult multi-talker babble at an approximate SNR of 0 dB.

The kidLUCID corpus is available online within the OSCAAR (Online Speech/Corpora Archive and Analysis Resource) archive (https://oscaar.ci.northwestern.edu/). Free access can be requested for research purposes. Further information about the project can be found at: http://www.ucl.ac.uk/pals/research/shaps/research/shaps/research/clear-speech-strategies

This work was supported by Economic and Social Research Council Grant No. RES-062- 23-3106.

Top

We are happy to announce the release of a table of 44 publicly available robust speech processing datasets and a table of 4 ASR software tools on the wiki of ISCA's Robust Speech Processing SIG:
https://wiki.inria.fr/rosp/Datasets#Speech_datasets
https://wiki.inria.fr/rosp/Software#Automatic_speech_recognition

We hope that these tables will promote wider dissemination of the datasets and software tools available in our community and help newcomers select the most suitable dataset or software for a given experiment. We plan to provide additional tables on, e.g., room impulse response datasets or speaker recognition software in the future.

We highly welcome your input, especially additional tables/entries and reproducible baselines for each dataset. It just takes a few minutes thanks to the simple wiki interface.

For more information about joining the SIG and contributing, see
https://wiki.inria.fr/rosp/

Jonathan Le Roux, Emmanuel Vincent, and Ramon Astudillo

Top

ELRA and LDC partner to implement ISLRN process and assign identifiers to all the Language Resources in their catalogues.

Following the meeting of the largest NLP organizations, the NLP12, and their endorsement of the International Standard Language Resource Number (ISLRN), ELRA and LDC partnered to implement the ISLRN process and to assign identifiers to all the Language Resources (LRs) in their catalogues. The ISLRN web portal was designed to enable the assignment of unique identifiers as a service free of charge for all Language Resource providers. To enhance the use of ISLRN, ELRA and LDC have collaborated to provide the ISLRN 13-digit ID to all the Language Resources distributed in their respective catalogues. Anyone who is searching the ELRA and LDC catalogues can see that each Language Resource is now identified by both the data centre ID and the ISLRN number. All providers and users of such LRs should refer to the latter in their own publications and whenever referring to the LR.

ELRA and LDC will continue their joint involvement in ISLRN through active participation in this web service.

Visit the ELRA and LDC catalogues, respectively at http://catalogue.elra.info and https://catalog.ldc.upenn.edu

Background

The International Standard Language Resource Number (ISLRN) aims to provide unique identifiers using a standardised nomenclature, thus ensuring that LRs are correctly identified, and consequently, recognised with proper references for their usage in applications within R&D projects, product evaluation and benchmarking, as well as in documents and scientific papers. Moreover, this is a major step in the networked and shared world that Human Language Technologies (HLT) has become: unique resources must be identified as such and meta-catalogues need a common identification format to manage data correctly.

The ISLRN portal can be accessed from http://www.islrn.org,

***About NLP12***

Representatives of the major Natural Language Processing and Computational Linguistics organizations met in Paris on 18 November 2013 to harmonize and coordinate their activities within the field.
The results of this coordination are expressed in the Paris Declaration: http://www.elra.info/NLP12-Paris-Declaration.html.

*** About ELRA ***
The European Language Resources Association (ELRA) is a non-profit making organisation founded by the European Commission in 1995, with the mission of providing a clearing house for language resources and promoting Human Language Technologies (HLT).
To find out more about ELRA, please visit our web site: http://www.elra.info

*** About LDC ***

The Linguistic Data Consortium (LDC) is an open consortium of universities, libraries, corporations and research laboratories that creates and distributes linguistic resources for language-related education, research and technology development.

To find out more about LDC, please visit our web site: https://www.ldc.upenn.edu


For more information, please contact: admin@islrn.org

Top

JRC, the EC's Joint Research Centre, an important LR player: First to adopt the ISLRN initiative

The Joint Research Centre (JRC), the European Commission's in house science service, is the first organisation to use the International Standard Language Resource Number (ISLRN) initiative and has requested ISLRN 13-digit unique identifiers to its Language Resources (LR).
Thus, anyone who is using JRC LRs may now refer to this number in their own publications.

The current JRC LRs (downloadable from https://ec.europa.eu/jrc/en/language-technologies) with an ISLRN ID are:

• DGT-Acquis, ISLRN: 393-866-130-658-2
• DGT-TM, ISLRN: 710-653-952-884-4
• EAC-TM, ISLRN: 589-927-543-547-4
• ECDC-TM, ISLRN: 476-596-396-497-8
• English sentiment quotes, ISLRN: 574-735-957-886-6
• JRC-Acquis, ISLRN: 821-325-977-001-1
• JRC-Names, ISLRN: 328-863-023-410-2
• Multilingual summary evaluation data, ISLRN: 762-292-165-648-8
• Turkish Tweet Named Entity annotation, ISLRN: 764-177-227-350-7

Background

The International Standard Language Resource Number (ISLRN) aims to provide unique identifiers using a standardised nomenclature, thus ensuring that LRs are correctly identified, and consequently, recognised with proper references for their usage in applications within R&D projects, product evaluation and benchmarking, as well as in documents and scientific papers. Moreover, this is a major step in the networked and shared world that Human Language Technologies (HLT) has become: unique resources must be identified as such and meta-catalogues need a common identification format to manage data correctly.
The ISLRN portal can be accessed from http://www.islrn.org,

*** About the JRC ***

As the Commission's in-house science service, the Joint Research Centre's mission is to provide EU policies with independent, evidence-based scientific and technical support throughout the whole policy cycle.
Within its research in the field of global security and crisis management, the JRC develops open source intelligence and analysis systems that can automatically harvest and analyse a huge amount of multi-lingual information from the internet-based sources. In this context, the JRC has developed Language Technology resources and tools that can be used for highly multilingual text analysis and cross-lingual applications.
To find out more about JRC's research in open source information monitoring, please visit https://ec.europa.eu/jrc/en/research-topic/internet-surveillance-systems. To access media monitoring applications directly, go to http://emm.newsbrief.eu/overview.html.

*** About ELRA ***
The European Language Resources Association (ELRA) is a non-profit making organisation founded by the European Commission in 1995, with the mission of providing a clearing house for language resources and promoting Human Language Technologies (HLT).
To find out more about ELRA, please visit our web site: http://www.elra.info

For more information, contact admin@ilsrn.org
 

Top

Forensic database of voice recordings of 500+ Australian English speakers

We are pleased to announce that the forensic database of voice recordings of 500+ Australian English speakers is now published.

The database was collected by the Forensic Voice Comparison Laboratory, School of Electrical Engineering & Telecommunications, University of New South Wales as part of the Australian Research Council funded Linkage Project on making demonstrably valid and reliable forensic voice comparison a practical everyday reality in Australia. The project was conducted in partnership with: Australian Federal Police,  New South Wales Police,  Queensland Police, National Institute of Forensic Sciences, Australasian Speech Sciences and Technology Association, Guardia Civil, Universidad Autónoma de Madrid.

The database includes multiple non-contemporaneous recordings of most speakers. Each speaker is recorded in three different speaking styles representative of some common styles found in forensic casework. Recordings are recorded under high-quality conditions and extraneous noises and crosstalk have been manually removed. The high-quality audio can be processed to reflect recording conditions found in forensic casework.

The database can be accessed at: http://databases.forensic-voice-comparison.net/

Top

Audio and Electroglottographic speech recordings from several languages

We are happy to announce the public availability of speech recordings made as part of the UCLA project 'Production and Perception of Linguistic Voice Quality'.

http://www.phonetics.ucla.edu/voiceproject/voice.html

Audio and EGG recordings are available for Bo, Gujarati, Hmong, Mandarin, Black Miao, Southern Yi, Santiago Matatlan/ San Juan Guelavia Zapotec; audio recordings (no EGG) are available for English and Mandarin. Recordings of Jalapa Mazatec extracted from the UCLA Phonetic Archive are also posted. All recordings are accompanied by explanatory notes and wordlists, and most are accompanied by Praat textgrids that locate target segments of interest to our project.

Analysis software developed as part of the project – VoiceSauce for audio analysis and EggWorks for EGG analysis – and all project publications are also available from this site. All preliminary analyses of the recordings using these tools (i.e. acoustic and EGG parameter values extracted from the recordings) are posted on the site in large data spreadsheets.

All of these materials are made freely available under a Creative Commons Attribution-NonCommercial-ShareAlike-3.0 Unported License.

This project was funded by NSF grant BCS-0720304 to Pat Keating, Abeer Alwan and Jody Kreiman of UCLA, and Christina Esposito of Macalester College.

Pat Keating (UCLA)

Top

Press Release - Immediate - Paris, France, April 2, 2015

Opening of the ELRA License Wizard

ELRA announces the opening of the License Wizard @ http://wizard.elda.org.

ELRA  is deploying a License Wizard to:

• support the right-holders in finding the appropriate licenses under which to share/distribute their Language Resources, and
• clarify the legal obligations applicable in various licensing situations.

Currently, the License Wizard allows the user to choose among several licenses that exist for the use of Language Resources: ELRA, Creative Commons and META-SHARE.
More will be added.

The License Wizard works as a web configurator that helps Right Holders/Users:

- to select a number of legal features and obtain the user license adapted to their selection.
- to define which user licenses they would like to select in order to distribute their Language Resources.
- to integrate the user license terms into a Distribution Agreement that could be proposed to ELRA or META-SHARE  for further distribution through the ELRA Catalogue of Language Resources (http://catalogue.elra.info,  www.meta-share.eu).

Background
From the very beginning, ELRA has come across all types of legal issues that arise when exchanging and sharing Language Resources. The association has devoted huge efforts to streamline the licensing processes while continuously monitoring the impacts of regulation changes on the HLT community activities. The first major step was to come up with a few licenses for both the research and the industrial sectors to use the resources available within the ELRA catalogue. Recently, its strong involvement in the META-SHARE infrastructure led to designing and drafting a small set of licenses, inspired by the ELRA licenses but also accounting for the new trends of permissive licenses and free resources, represented in particular by the Creative Commons.

Top

We are making 24 GB of a new dataset, called Kara One, freely available. This database combines 3 modalities (EEG, face tracking, and audio) during imagined and articulated speech using phonologically-relevant phonemic and single-word prompts. It is the result of a collaboration between the Toronto Rehabilitation Institute (in the University Health Network) and the Department of Computer Science at the University of Toronto.

In the associated paper (abstract below), we show how to accurately classify imagined phonological categories solely from EEG data. Specifically, we obtain up to 90% accuracy in classifying imagined consonants from imagined vowels and up to 95% accuracy in classifying stimulus from active imagination states using advanced deep-belief networks.

Data from 14 participants are available here: http://www.cs.toronto.edu/~complingweb/data/karaOne/karaOne.html.

If you have any questions, please contact Frank Rudzicz at frank@cs.toronto.edu.

Best regards,

Frank

PAPER Shunan Zhao and Frank Rudzicz (2015) Classifying phonological categories in imagined and articulated speech. In Proceedings of ICASSP 2015, Brisbane Australia

ABSTRACT This paper presents a new dataset combining 3 modalities (EEG, facial, and audio) during imagined and vocalized phonemic and single-word prompts. We pre-process the EEG data, compute features for all 3 modalities, and perform binary classi?cation of phonological categories using a combination of these modalities. For example, a deep-belief network obtains accuracies over 90% on identifying consonants, which is signi?cantly more accurate than two baseline supportvectormachines. Wealsoclassifybetweenthedifferent states (resting, stimuli, active thinking) of the recording, achievingaccuraciesof95%. Thesedatamaybeusedtolearn multimodal relationships, and to develop silent-speech and brain-computer interfaces.

Top

In the spirit of the season, I would like to announce the immediate availability of the TORGO database free, in perpetuity for academic use. This database combines acoustics and electromagnetic articulography from 8 individuals with speech disorders and 7 without, and totals over 18 GB. These data can be used for multimodal models (e.g., for acoustic-articulatory inversion), models of pathology, and augmented speech recognition, for example. More information (and the database itself) can be found here: http://www.cs.toronto.edu/~complingweb/data/TORGO/torgo.html.

Top

Datatang is a global leading data provider that specialized in data customized solution, focusing in variety speech, image, and text data collection, annotation, crowdsourcing services.

1, Speech data collection

2, Speech data synthesis

3, Speech data transcription

I’ve attached our company introduction as reference, as well as available speech data lists as follows:

If you find any particular interested datasets, we could provide you samples with costs too.

Regards

Runze Zhao

zhaorunze@datatang.com 

Oversea Sales Manager | Datatang Technology 

China

M: +86 185 1698 2583

18 Zhongguancun St.

Kemao Building Tower B 18F

Beijing 100190

US

M: +1 617 763 4722 

640 W California Ave, Suite 210

Sunnyvale, CA 94086

Top

In this newsletter:

LDC Director Mark Liberman receives the IEEE James L. Flanagan Speech and Audio Processing Award

Only two weeks left to enjoy 2017 membership discounts

Spring 2016 LDC Data Scholarship recipients

New publications:

First-Year Law Students' Court Memoranda

IARPA Babel Haitian Creole Language Pack IARPA-babel201b-v0.2b

GALE Phase 3 Arabic Broadcast News Speech Part 2

GALE Phase 3 Arabic Broadcast News Transcripts Part 2

LDC Director Mark Liberman receives the IEEE James L. Flanagan Speech and Audio Processing Award

LDC Director Mark Liberman is the 2017 recipient of the IEEE James L. Flanagan Speech and Audio Processing Award. Established in 2002, this annual award recognizes an individual for his or her outstanding contribution to the advancement of speech and/or audio processing. Liberman’s pioneering contributions and continued leadership in robust, replicable, and data-driven speech and language science and engineering have fueled the development and advancement of human language technologies including speech and speaker recognition, machine translation, and semantic analysis. As LDC’s founder, Mark has shepherded the Consortium from a small organization to the largest developer of shared language resources, distributing more than 120,000 copies of over 2,000 databases covering 91 different languages to more than 3,600 organizations in over 70 countries. 

Liberman will receive the award at ICASSP 2017 in New Orleans (March 5-9). LDC will be an exhibitor at Booth 43. Please stop by and say hello. We hope to see you there.   

Only two weeks left to enjoy 2017 membership discounts

There is still time to save on 2017 membership fees. Through March 1, all organizations receive a discount on the 2017 membership fee (up to 10%) when they choose to join or renew.   

For more information on membership benefits, visit Join LDC.

Spring 2016 LDC Data Scholarship recipients

Congratulations to the recipients of LDC's Spring 2017 data scholarship:

Umad Ul Hassan and Muhammad Awais Zulfiqar: National University of Sciences and Technology (Pakistan); BS Computer Science. Hassan and Zulfiqar are awarded copies of CSLU: Kids’ Speech Version 1.1 and The CMU Kids Corpus for their research in speech recognition for children with learning difficulties.

For information about the program, visit the Data Scholarship page.

New publications:

(1) First-Year Law Students' Court Memoranda consists of 197 English law student writing samples of legal briefs annotated for certain characteristics along with accompanying survey responses by student writers.

The briefs were created in a law school writing class at two law schools in the US Midwest during the 2011-12 academic year. Students who agreed to participate in this study uploaded their briefs to an online survey instrument and answered questions regarding their age, gender, level of education, most recent writing course and method of learning English. The study's purpose was to apply natural language processing approaches to determine any differences in the briefs' language attributable to the students' self-reported genders.

The samples were imported into the General Architecture for Text Engineering (GATE) and annotated by two human coders who identified large text segments specific to the legal genre in which the students wrote, such as text headings, citations, block quotes and footnotes.

Writing samples are presented as MS Word documents and annotations and survey responses are presented in XML format. The data has been anonymized to remove names and other identifying information about the student participants.

First-Year Law Students' Court Memoranda is distributed via web download.

2017 Subscription Members will receive copies of this corpus provided they have submitted a completed copy of the special license agreement. 2017 Standard Members may request a copy as part of their 16 free membership corpora. Non-members may license this data for US $250.

*

(2) IARPA Babel Haitian Creole Language Pack IARPA-babel201b-v0.2b was developed by Appen for the IARPA (Intelligence Advanced Research Projects Activity) Babel program. It contains approximately 203 hours of Haitian Creole conversational and scripted telephone speech collected in 2012 and 2013 along with corresponding transcripts.

The Babel program focuses on underserved languages and seeks to develop speech recognition technology that can be rapidly applied to any human language to support keyword search performance over large amounts of recorded speech.

The Haitian Creole speech in this release represents that spoken in the Northern, Western and Southern dialect regions in Haiti. The gender distribution among speakers is approximately equal; speakers' ages range from 16 years to 75 years. Calls were made using different telephones (e.g., mobile, landline) from a variety of environments including the street, a home or office, a public place, and inside a vehicle.

Transcripts are encoded in UTF-8.

IARPA Babel Haitian Creole Language Pack IARPA-babel201b-v0.2b is distributed via web download.

2017 Subscription Members will receive copies of this corpus provided they have submitted a completed copy of the special license agreement. 2017 Standard Members may request a copy as part of their 16 free membership corpora. Non-members may license this data for US $25.

*

(3) GALE Phase 3 Arabic Broadcast News Speech Part 2 was developed by LDC and is comprised of approximately 128 hours of Arabic broadcast conversation speech collected in 2007 by LDC, MediaNet, Tunis, Tunisia and MTC, Rabat, Morocco during Phase 3 of the DARPA GALE (Global Autonomous Language Exploitation) program.

Corresponding transcripts are released as GALE Phase 3 Arabic Broadcast News Transcripts Part 2 (LDC2017T04).

The recordings in this corpus feature news broadcasts focusing principally on current events from various broadcast programmers including Abu Dhabi TV, Al Alam News Channel, Al Arabiya, Al Iraqiyah, Aljazeera, Al Ordiniyah, Dubai TV, Kuwait TV, Lebanese Broadcast Corporation, Nile TV, Saudi TV and Syria TV.

This release contains 175 audio files presented in FLAC-compressed Waveform Audio File format (.flac), 16000 Hz single-channel 16-bit PCM. Each file was audited by a native Arabic speaker.

GALE Phase 3 Arabic Broadcast News Speech Part 2 is distributed via web download.

2017 Subscription Members will automatically receive copies of this corpus. 2017 Standard Members may request a copy as part of their 16 free membership corpora. Non-members may license this data for US $2000.

*

(4) GALE Phase 3 Arabic Broadcast News Transcripts Part 2 was developed by LDC and contains transcriptions of approximately 128 hours of Arabic broadcast news speech collected in 2007 by LDC, MediaNet, Tunis, Tunisia and MTC, Rabat, Morocco during Phase 3 of the DARPA GALE (Global Autonomous Language Exploitation) program.

Corresponding audio data is released as GALE Phase 3 Arabic Broadcast News Speech Part 2 (LDC2017S02). 

The transcript files are in plain-text, tab-delimited format (TDF) with UTF-8 encoding, and the transcribed data totals 721,846 tokens. The transcripts were created with the LDC tool, XTrans, which supports manual transcription and annotation of audio recordings.

The files in this corpus were transcribed by LDC staff and/or by transcription vendors under contract to LDC. Transcribers followed LDC's quick transcription guidelines (QTR) and quick rich transcription specification (QRTR) both of which are included in the documentation with this release.

GALE Phase 3 Arabic Broadcast News Transcripts Part 2 is distributed via web download.

2017 Subscription Members will automatically receive copies of this corpus. 2017 Standard Members may request a copy as part of their 16 free membership corpora. Non-members may license this data for US $1500.

Membership Office

Linguistic Data Consortium

University of Pennsylvania

T: +1-215-573-1275

E: ldc@ldc.upenn.edu

M: 3600 Market St. Suite 810

      Philadelphia, PA 19104

Top

ROCme!: nouveau logiciel gratuit pour l'enregistrement et la gestion de corpus audio.

Le logiciel ROCme! permet une gestion rationalisée, autonome et dématérialisée de l’enregistrement de corpus lus.

Caractéristiques clés :
- gratuit
- compatible Windows et Mac
- interface paramétrable pour le recueil de métadonnées sur les locuteurs
- le locuteur fait défiler les phrases à l'écran et les enregistre de façon autonome
- format audio paramétrable

Téléchargeable à cette adresse :
www.ddl.ish-lyon.cnrs.fr/rocme

Top

VocalTractLab 2.0 : A tool for articulatory speech synthesis

It is my pleasure to announce the release of the new major version 2.0 of VocalTractLab. VocalTractLab is an articulatory speech synthesizer and a tool to visualize and explore the mechanism of speech production with regard to articulation, acoustics, and control. It is available from http://www.vocaltractlab.de/index.php?page=vocaltractlab-download .
Compared to version 1.0, the new version brings many improvements in terms of the implemented models of the vocal tract, the vocal folds, the acoustic simulation, and articulatory control, as well as in terms of the user interface. Most importantly, the new version comes together with a manual.

If you like, give it a try. Reports on bugs and any other feedback are welcome.

Peter Birkholz

Top

    The release 1.2.0 of the Bob signal-processing and machine learning toolbox is available .
    Bob provides both efficient implementations of several machine     learning algorithms as well as a framework to help researchers to     publish reproducible research.
   
   

   
    The previous release of Bob was providing:
    * image, video and audio IO interfaces such as jpg, avi, wav, 
    * database accessors such as FRGC, Labelled Face in the Wild, and many     others,
    *mage processing: Local Binary Patterns (LBPs), Gabor Jets,  SIFT,
    * machines  and trainers such as Support Vector Machines (SVMs), k-Means,     Gaussian Mixture Models (GMMs), Inter-Session Variability modeling     (ISV), Joint Factor Analysis (JFA), Probabilistic Linear     Discriminant Analysis (PLDA), Bayesian intra/extra (personal)     classifier,
   
    The new release of Bob has brought the following features and/or improvements, such as:
    * Unified implementation of Local Binary Patterns (LBPs),
    * Histograms of Oriented Gradients (HOG) implementation,
    * Total variability (i-vector) implementation,
    * Conjugate gradient based-implementation for logistic regression,
    * Improved multi-layer perceptrons implementation (Back-propagation can now be easily used in combination with any optimizer -- i.e     L-BFGS),
    * Pseudo-inverse-based method for Linear Discriminant Analysis,
    * Covariance-based method for Principal Component Analysis,
    * Whitening and within-class covariance normalization techniques,
    * Module for object detection and keypoint localization     (bob.visioner),
    * Module for audio processing including feature extraction such as LFCC and     MFCC,
    * Improved extensions (satellite packages), that now support both     Python and C++ code, within an easy to use framework,
    * Improved documentation and add new tutorials,
    * Support for Intel's MKL (in addition to ATLAS),
    * Extend supported platforms (Arch Linux).
   
    This release represents a major milestone in Bob with plenty of  functionality improvements (>640 commits in total) and plenty of bug fixes.
    • Sources and Documentation
    • Binary packages:
    •     Ubuntu: 10.04, 12.04, 12.10 and 13.04
    • For     Mac OSX: works with 10.6 (Snow Leopard), 10.7 (Lion) and 10.8     (Mountain Lion)
   
    For instructions on how to install pre-packaged version on Ubuntu or     OSX, consult our quick       installation instructions  (N.B. OS X macport has not yet been     upgraded. This will be done very soon. cf. https://trac.macports.org/ticket/39831 ).
   
   
    Best regards,
    Elie Khoury (on Behalf of the Biometric Group at Idiap lead by Sebastien Marcel)
   
     
     ---    

 Dr. Elie Khoury Post Doctorant Biometric Person Recognition Group 

IDIAP Research Institute (Switzerland) Tel : +41 27 721 77 23

Top

Release of the version 2 of FASST (Flexible Audio Source Separation Toolbox). http://bass-db.gforge.inria.fr/fasst/ This toolbox is intended to speed up the conception and to automate the implementation of new model-based audio source separation algorithms. It has the following additions compared to version 1: * Core in C++ * User scripts in MATLAB or python * Speedup * Multichannel audio input We provide 2 examples: 1. two-channel instantaneous NMF 2. real-world speech enhancement (2nd CHiME Challenge, Track 1)

Top

We are glad to announce the public realease of the Cantor Digitalis, an open-source real-time singing synthesizer controlled by hand gestures.

Top

We are happy to announce the release of our new toolkit “MultiVec” for computing continuous representations for text at different granularity levels (word-level or sequences of words). MultiVec includes Mikolov et al. [2013b]’s word2vec features, Le and Mikolov [2014]’s paragraph vector (batch and online) and Luong et al. [2015]’s model for bilingual distributed representations. MultiVec also includes different distance measures between words and sequences of words. The toolkit is written in C++ and is aimed at being fast (in the same order of magnitude as word2vec), easy to use, and easy to extend. It has been evaluated on several NLP tasks: the analogical reasoning task, sentiment analysis, and crosslingual document classification. The toolkit also includes C++ and Python libraries, that you can use to query bilingual and monolingual models.

The project is fully open to future contributions. The code is provided on the project webpage (https://github.com/eske/multivec) with installation instructions and command-line usage examples.

When you use this toolkit, please cite:

@InProceedings{MultiVecLREC2016,

Title                    = {{MultiVec: a Multilingual and MultiLevel Representation Learning Toolkit for NLP}},

Author                   = {Alexandre Bérard and Christophe Servan and Olivier Pietquin and Laurent Besacier},

Booktitle                = {The 10th edition of the Language Resources and Evaluation Conference (LREC 2016)},

Year                     = {2016},

Month                    = {May}

}

The paper is available here: https://github.com/eske/multivec/raw/master/docs/Berard_and_al-MultiVec_a_Multilingual_and_Multilevel_Representation_Learning_Toolkit_for_NLP-LREC2016.pdf

Best regards,

Alexandre Bérard, Christophe Servan, Olivier Pietquin and Laurent Besacier

Top

11th Oxford Dysfluency Conference 
Challenge and Change

Top

It is our pleasure to introduce A||GO (https://allgo.inria.fr/ or http://allgo.irisa.fr/), a platform providing a collection of web-services for the automatic analysis of various data, including multimedia content across modalities. The platform builds on the back-end web service deployment infrastructure developed and maintained by  Inria?s  Service for Experimentation and Development (SED). Originally dedicated to multimedia content, A||GO progressively broadened to other fields such as computational biology, networks and telecommunications, computational graphics or computational physics.

As part of the CNRS PlaSciDo initiative [1], the Linkmedia team at IRISA / Inria Rennes is making available via A||GO a number of web services devoted to multimedia content analysis across modalities (language, audio, image, video). The web services provided currently include research results from the Linkmedia team as well as contribution from a number of partners. A list of the services available by the date is given below and the current state is available at https://www-linkmedia.irisa.fr/software along with demo videos. Most web services are interoperable, facilitating the implementation of a multimedia content analysis processing chain, and are free to use for trial, prototyping or lab work. A brief and free account creation step will allow you to execute the web-services using either the graphical interface or a command line via a dedicated API.

We expect the number of web services to grow over time and invite interested parties to contact us should they wish to contribute the multimedia web service offer of A||GO.

List of multimedia content analysis tools currently available on A||GO:
- Audio Processing
        SaMuSa: music/speech segmentation
        SilAD: silence detection
        Radi.sh: repeated audio motif discovery
        LORIA STS v2: speech transcription for the French language from LORIA
        Multi channel BSS locate: audio source localization toolbox from IRISA-PANAMA
        A-spade: audio declipper from IRISA-PANAMA
        Transvox: voice faker from LORIA
- Natural Language Processing
        NERO: name entity recognition
        TermEx: keywords/indexing terms detection
        Otis!: topic segmentation
        Hi-tost: hierarchical topic structuring
- Video Processing
        Vidseg: video shot segmentation
        HUFA: face detection and tracking
Shortcuts to Linkmedia services are also available here: https://www-linkmedia.irisa.fr/software/
 
For more information don't hesitate to contact us (contact-multimedia-allgo@irisa.fr). 

 
Gabriel Sargent and Guillaume Gravier
--
Linkmedia
IRISA - CNRS
Rennes, France

Top