Aims and Scope
With the rapid advancement in microelectronics and parallel computing, significant computational power is nowadays readily available in ever smaller battery-operated consumer electronics devices. This has paved the way for applications such as active noise cancellation (ANC) headphones, hearing protectors, communication headsets, 3-D glasses, to name a few. In addition, hearing aids have also experienced large advances in electronics and functionality. To a large extent this rapid development can be attributed to the popularity of mobile phones, as these devices are no longer used merely as a communication tool but are multi-media and gaming platforms. Accordingly they require sophisticated processing for augmented reality in which the virtual listening world can be combined conveniently with situational acoustical awareness. The same can be said for assistive listening devices (ALDs), including hearing aids, personal sound amplification devices, and related audio capture accessories. Here the challenge is to render the sound as accessible as possible in order to provide hearing support in challenging acoustical situations. All aforementioned applications are underpinned by fundamental signal processing problems related to sound capture and sound rendering. On the one hand, for sound capture problems such as sensor technology (microphones, accelerometers etc.), acoustic scene analysis, audio signal enhancement, noise suppression with single and multiple sensors, feedback suppression and dereverberation need to be considered. On the other hand, sound rendering involves problems such as active noise cancellation, loudspeaker equalization (for mimicking or adapting outer-ear characteristics), 3-D audio rendering, acoustic scene visualization, automatic mixing and psycho-acoustical processing.

This special issue focuses on technical challenges of assisted listening from a signal processing perspective. Prospective authors are invited to contribute tutorial and survey articles that articulate signal processing methodologies which are critical for applying assisted listening techniques to mobile phones and other communication devices. Of particular interest is the role of signal processing in combining multimedia content, voice communication and voice pick-up in various real-world settings.

Tutorial and survey papers are solicited on advances in signal processing that particularly apply to the following applications:

• Assistive listening devices, hearing aids and personal sound amplifiers
• Communication devices
• Hearing protection and active noise control
• Navigation systems

These can include the following suggested topics as they relate to the above applications:

Submission Process
Articles submitted to this special issue must contain significant relevance to advanced acoustic signal processing enabling assisted listening. All submissions will be peer reviewed according to the IEEE and Signal Processing Society guidelines for both publications. Submitted articles should not have been published or be under review elsewhere. Manuscripts should be submitted online at http://mc.manuscriptcentral.com/sps-ieee using the Manuscript Central interface. Submissions to this special issue of the IEEE SIGNAL PROCESSING MAGAZINE should have significant tutorial value. Prospective authors should consult the site http://www.signalprocessingsociety.org/publications/periodicals/spm/ for guidelines and information on paper submission.

Important Dates: Expected publication date for this special issue is March 2015.

Guest Editors
Sven Nordholm, Lead GE, Curtin University, Perth, Western Australia (s.nordholm@curtin.edu.au)
Walter Kellermann, Friedrich-Alexander University, Erlangen-Nuremberg, Germany (wk@lnt.de)
Simon Doclo, University of Oldenburg, Oldenburg, Germany (simon.doclo@uni-oldenburg.de)
Vesa Välimäki, Aalto University, Espoo, Finland (vesa.valimaki@alto.fi)
Shoji Makino, University of Tsukuba, Tsukuba, Japan (maki@tara.tsukuba.ac.jp)
John Hershey, Mitsubishi Electric Research Laboratories, Boston, USA (hershey@merl.com)

Back

Top

Special Issue of ACM Transactions on Accessible Computing (TACCESS) On

Speech and Language Interaction for Daily Assistive Technology

Guest Editors: François Portet, Frank Rudzicz, Jan Alexandersson, Heidi Christensen

Assistive technologies (AT) allow individuals with disabilities to do things that would otherwise be difficult or impossible. Many assistive technologies involve providing universal access, such as modifications to televisions or telephones to make them accessible to those with vision or hearing impairments. An important sub-discipline within this community is Augmentative and Alternative Communication (AAC), which has its focus on communication technologies for those with impairments that interfere with some aspect of human communication, including spoken or written modalities. Another important sub-discipline is Ambient Assisted Living (AAL) which facilitates independent living; these technologies break down the barriers faced by people with physical or cognitive impairments and support their relatives and caregivers. These technologies are expected to improve quality-of-life of users and promote independence, accessibility, learning, and social connectivity.

Speech and natural language processing (NLP) can be used in AT/AAC in a variety of ways including, improving the intelligibility of unintelligible speech, and providing communicative assistance for frail individuals or those with severe motor impairments. The range of applications and technologies in AAL that can rely on speech and NLP technologies is very large, and the number of individuals actively working within these research communities is growing, as evidenced by the successful INTERSPEECH 2013 satellite workshop on Speech and Language Processing for Assistive Technologies (SLPAT). In particular, one of the greatest challenges in AAL is to design smart spaces (e.g., at home, work, hospital) and intelligent companions that anticipate user needs and enable them to interact with and in their daily environment and provide ways to communicate with others. This technology can benefit each of visually-, physically-, speech- or cognitively- impaired persons.

Topics of interest for submission to this special issue include (but are not limited to):

• Speech, natural language and multimodal interfaces designed for people with physical or cognitive impairments
• Applications of speech and NLP technology (automatic speech recognition, synthesis, dialogue, natural language generation) for AT applications
• Novel modeling and machine learning approaches for AT applications
• Long-term adaptation of speech/NLP based AT system to user's change
• User studies, overview of speech/NLP technology for AT: understanding the user's needs and future speech and language based technologies.
• Understanding, modeling and recognition of aged or disordered speech
• Speech analysis and diagnosis: automatic recognition and detection of speech pathologies and speech capability loss
• Speech-based distress recognition
• Automated processing of symbol languages, sign language and nonverbal communication including translation systems.
• Text and audio processing for improved comprehension and intelligibility, e.g., sentence simplification or text-to-speech
• Evaluation methodology of systems and components in the lab and in the wild.
• Resources; corpora and annotation schemes
• Other topics in AAC, AAL, and AT

Submission process

Contributions must not have been previously published or be under consideration for publication elsewhere, although substantial extensions of conference or workshop papers will be considered. as long as they adhere to ACM's minimum standards regarding prior publication (http://www.acm.org/pubs/sim_submissions.html). Studies involving experimentations with real target users will be appreciated. All submissions have to be prepared according to the Guide for Authors as published in the Journal website at http://www.rit.edu/gccis/taccess/. 

Submissions should follow the journal's suggested writing format (http://www.gccis.rit.edu/taccess/authors.html) and should be submitted through Manuscript Central http://mc.manuscriptcentral.com/taccess , indicating that the paper is intended for the Special Issue. All papers will be subject to the peer review process and final decisions regarding publication will be based on this review.

Important dates:

◦              Extended deadline for full paper submission: 28th April 2014

◦              Response to authors: 30^th June 2014

◦              Revised submission deadline: 31^st August 2014

◦              Notification of acceptance: 31^st October 2014

◦              Final manuscripts due: 30^th November 2014

Back

Top

Spatial audio is an area that has gained in popularity in the recent years. Audio reproduction setups evolved from the traditional two-channel loudspeaker setups towards multi-channel loudspeaker setups. Advances in acoustic signal processing even made it possible to create a surround sound listening experience using traditional stereo speakers and headphones. Finally, there has been an increased interest in creating different sound zones in the same acoustic space (also referred to as personal audio). At the same time, the computational capacity provided by mobile audio playback devices has increased significantly. These developments enable new possibilities for advanced audio signal processing, such that in the future we can record, transmit and reproduce spatial audio in ways that have not been possible before. In addition, there have been fundamental advances in our understanding of 3D audio.

Due to the increasing number of different formats and reproduction systems for spatial audio, ranging from headphones to 22.2 speaker systems, it is major challenge to ensure interoperability between formats and systems, and consistent delivery of high-quality spatial audio. Therefore, the MPEG committee is in the process of establishing new standards for 3D Audio Content Delivery.

The scope of this Special Issue on Spatial Audio is open to contributions ranging from the measurement and modeling of an acoustic space to reproduction and perception of spatial audio. While individual submissions may focus on any of the sub-topics listed below, papers describing a larger spatial audio signal processing systems will be considered as well.

We invite authors to address some of the following spatial audio aspects:

• Capture of Spatial Sound, use of different microphone arrays to record 3D sound fields
• Loudspeaker and Headphone Reproduction of Spatial Sound, including e.g. wave field synthesis, Ambisonics, arbitrary multi-channel loudspeaker setups, cross-talk cancellation systems, and personal audio systems
• Spatial Sound Processing including e.g. downmixing, upmixing, spatial sound enhancement, and reverberation effects
• Sound Source Localization and Room Geometry Estimation, advanced analysis of audio signals for reconstruction of the acoustic environment
• Room Acoustics Modeling covering all different modeling techniques ranging from computationally heavy wave-based techniques and geometrical acoustics to lightweight perceptually-based models.

Prospective authors should visit http://www.signalprocessingsociety.org/publications/periodicals/jstsp/ for information on paper submission. Manuscripts should be submitted at http://mc.manuscriptcentral.com/jstsp-ieee.

Manuscript Submission: July 1, 2014
First Review Due: October 15, 2014
Revised Manuscript: December 1, 2014
Second Review Due: February 1, 2015
Final Manuscript: March 1, 2015

Guest Editors:
Lauri Savioja, Aalto University, Finland (Lauri.Savioja@aalto.fi)
Akio Ando, University of Toyama, Japan (andio@eng.u-toyama.ac.jp)
Ramani Duraiswami, University of Maryland, USA (ramani@umiacs.umd.edu)
Emanuël Habets, Int. Audio Laboratories Erlangen, Germany (emanuel.habets@audiolabs-erlangen.de)
Sascha Spors, Universität Rostock, Germany (sascha.spors@uni-rostock.de)

Back

Top

***** Journal of Natural Language Engineering - Special Issue on “Machine Translation Using Comparable Corpora” *****

CALL FOR PAPERS Statistical machine translation based on parallel corpora has been very successful. The major search engines' translation systems, which are used by millions of people, are primarily using this approach, and it has been possible to come up with new language pairs in a fraction of the time that would be required when using more traditional rule-based methods. In contrast, research on comparable corpora is still at an earlier stage. Comparable corpora can be defined as monolingual corpora covering roughly the same subject area in different languages but without being exact translations of each other. However, despite its tremendous success, the use of parallel corpora in MT has a number of drawbacks: 1) It has been shown that translated language is somewhat different from original language, for example Klebanov & Flor showed that 'associative texture' is lost in translation. 2) As they require translation, parallel corpora will always be a far scarcer resource than comparable corpora. This is a severe drawback for a number of reasons: a) Among the about 7000 world languages, of which 600 have a written form, the vast majority are of the 'low resource' type. b) The number of possible language pairs increases with the square of the number of languages. When using parallel corpora, one bitext is needed for each language pair. When using comparable corpora, one monolingual corpus per language suffices. c) For improved translation quality, translation systems specialized on particular genres and domains are desirable. But it is far more difficult to acquire appropriate parallel rather than comparable training corpora. d) As language evolves over time, the training corpora should be updated on a regular basis. Again, this is more difficult in the parallel case. For such reasons it would be a big step forward if it were possible to base statistical machine translation on comparable rather than on parallel corpora: The acquisition of training data would be far easier, and the unnatural 'translation bias' (source language shining through) within the training data could be avoided. But is there any evidence that this is possible? Motivation for using comparable corpora in MT research comes from a cognitive perspective: Experience tells that persons who have learned a second language completely independently from their mother tongue can nevertheless translate between the languages. That is, human performance shows that there must be a way to bridge the gap between languages which does not rely on parallel data. Using parallel data for MT is of course a nice shortcut. But avoiding this shortcut by doing MT based on comparable corpora may well be a key to a better understanding of human translation, and to better MT quality. Work on comparable corpora in the context of MT has been ongoing for almost 20 years. It has turned out that this is a very hard problem to solve, but as it is among the grand challenges in multilingual NLP, interest has steadily increased. Apart from the increase in publications this can be seen from the considerable number of research projects (such as ACCURAT and TTC) which are fully or partially devoted to MT using comparable corpora. Given also the success of the workshop series on “Building and Using Comparable Corpora“ (BUCC), which is now in its seventh year, and following the publication of a related book (http://www.springer.com/computer/ai/book/978-3-642-20127-1), we think that it is now time to devote a journal special issue to this field. It is meant to bundle the latest top class research, make it available to everybody working in the field, and at the same time give an overview on the state of the art to all interested researchers.

TOPICS OF INTEREST We solicit contributions including but not limited to the following topics: • Comparable corpora based MT systems (CCMTs) • Architectures for CCMTs • CCMTs for less-resourced languages • CCMTs for less-resourced domains • CCMTs dealing with morphologically rich languages • CCMTs for spoken translation • Applications of CCMTs • CCMT evaluation • Open source CCMT systems • Hybrid systems combining SMT and CCMT • Hybrid systems combining rule-based MT and CCMT • Enhancing phrase-based SMT using comparable corpora • Expanding phrase tables using comparable corpora • Comparable corpora based processing tools/kits for MT • Methods for mining comparable corpora from the Web • Applying Harris' distributional hypothesis to comparable corpora • Induction of morphological, grammatical, and translation rules from comparable corpora • Machine learning techniques using comparable corpora • Parallel corpora vs. pairs of non-parallel monolingual corpora • Extraction of parallel segments or paraphrases from comparable corpora • Extraction of bilingual and multilingual translations of single words and multi-word expressions, proper names, and named entities from comparable corpora

IMPORTANT DATES December 1, 2014: Paper submission deadline February 1, 2015: Notification May 1, 2015: Deadline for revised papers July 1, 2015: Final notification September 1, 2015: Final paper due

GUEST EDITORS Reinhard Rapp, Universities of Aix Marseille (France) and Mainz (Germany) Serge Sharoff, University of Leeds (UK) Pierre Zweigenbaum, LIMSI, CNRS (France) FURTHER INFORMATION Please use the following e-mail address to contact the guest editors: jnle.bucc (at) limsi (dot) fr Further details on paper submission will be made available in due course at the BUCC website: http://comparable.limsi.fr/bucc2014/bucc-introduction.html

Back

Top

Le numéro spécial 54-2 de la revue TAL, intitulé 'Entitées Nommées',
coordonné par Sophia Ananiadou, Nathalie Friburger, Sophie Rosset est
maintenant en ligne à l'adresse suivante :
http://www.atala.org/-Entites-Nommees-

Sommaire :

Sophia Ananiadou, Nathalie Friburger, Sophie Rosset 
Préface http://www.atala.org/Preface,692

Damien Nouvel, Jean-Yves Antoine, Nathalie Friburger, Arnaud Soulet 
Fouille de règles d'annotation pour la reconnaissance d'entités nommées (http://www.atala.org/Fouille-de-regles-d-annotation)

Mohamed Hatmi, Christine Jacquin, Sylvain Meignier, Emmanuel Morin, Solen Quiniou 
Intégration de la reconnaissance des entités nommées au processus de reconnaissance de la parole (http://www.atala.org/Integration-de-la-reconnaissance)

Wei Wang, Romaric Besançon, Olivier Ferret, Brigitte Grau 
Extraction et regroupement de relations entre entités pour l'extraction d'information non supervisée (http://www.atala.org/Extraction-et-regroupement-de)

Souhir Gahbiche-Braham, Hélène Bonneau-Maynard, François Yvon 
Traitement automatique des entités nommées en arabe : détection et traduction (http://www.atala.org/Traitement-automatique-des-entites) 

Notes de lecture http://www.atala.org/Notes-de-lecture,687

Résumés de thèses http://www.atala.org/Resumes-de-these,686

Back

Top

Manuscript due: Dec. 1, 2014

Journal: Speech Communication

Description:

Sparse and low-rank modeling aim to incorporate the low-dimensional
structures pertained to the geometry of the underlying problems to
achieve the optimal solution. These concepts have been proven to be very
effective for a wide range of applications at the intersection of
multiple fields, including machine learning, signal processing and
statistics.

In the context of audio and speech processing, and more particularly
multiparty communications in reverberant and overlapping conditions, the
integration of sparse and low-rank modeling concepts has lead to several
interesting new directions and promising results in speech communication
problems, ranging from denoising to deconvolution and from separation to
recognition. Several other exciting developments include sparse linear
prediction, missing data recovery, audio content analysis and
inpainting. Addressing such real applications is particularly
challenging due to the complex acoustic and speech characteristics, and
the need to develop new modeling strategies that meet the foundational
theoretical hypotheses. In addition, speech recognition performance
seems to degrade in these complex acoustic conditions, and thus research
in this direction is critical from both a theoretical and industry
perspective.

The goal of the proposed special issue is to consolidate the research in
these diverse fields in a coherent framework and overview the recent
advances and trends where sparse and low-rank modeling and applications
are converging to new fundamental and practical paradigms that could
also lead to the emergence of new speech technologies.



Topics of interest include:

* Manifold learning in speech processing: single and multi-microphone
speech enhancement
* Sparse modeling and low-rank modeling for separation and denoising
* Sparse regression and classification
* Sparse dimensionality reduction for feature extraction
* Structured sparsity models underlying audio and speech representation
* Auditory-inspired sparse modeling
* Sparse modeling and low-rank modeling for source localization
* Sparse representation and low-rank representation for reverberant
acoustic modeling
* Sparse data processing and modeling in low-resourced languages
* Applications in speech recognition, privacy-preserving speech
processing, speaker recognition and authentication, speaker diarization,
microphone array calibration, audio information retrieval, speech
synthesis and coding

Lead Guest Editors:

* Prof. Hervé Bourlard, herve.bourlard@idiap.ch
* Dr. Afsaneh Asaei, afsaneh.asaei@idiap.ch
* Dr. Tara N. Sainath, tsainath@us.ibm.com
* Prof. Sharon Gannot, sharon.gannot@biu.ac.il

For more information about this special issue, please visit:

http://si.eurasip.org/issues/36/advances-in-sparse-modeling-and-low-rank-modeling/
_______________________________________________

Back

Top