Manuscript due: Nov. 1, 2013  

Journal: EURASIP Journal on Audio, Speech, and Music Processing Description: 

This special issue originates from a special session at the international conference Interspeech,

 which was held in September 2010 at Chiba, Japan. It will publish some key contributions 

presented at the conference describing different aspects of models of speech, from the analyisis 

or representation point of view. Topics of interest include: 

* Hidden Markov Models 

* Kernel Methods 

* Deep Neural Networks 

* Linear Predicitve Analysis 

Lead Guest Editor: 

* Hansjörg Mixdorff, Beuth University, Berlin, Germany Guest Editor: 

* Hideki Kawahara, Wakayama University, Wakayama, Japan 

For more information about this special issue, 

please visit: http://si.eurasip.org/issues/14/models-of-speech-in-search-of-better/

Top

Manuscript due: Feb. 1, 2014 Journal: EURASIP Journal on Audio, Speech, and Music Processing Description: With speech processing technology becoming more and more present in our every-day lives, it has become increasingly important to include all types of voices, speaking situations, and styles from all parts of our society, i.e., to move beyond the “typical”. Examples of such less typical patterns may include speaking while eating, during physical exercise, singing, as well as a wide range of pathological effects or speech generated by special aged groups (children, elderly). In fact, recent advances in the field of Computational Paralinguistics allow for automatic recognition, analysis, and synthesis of an ever-increasing range of “atypical” phenomena. At the same time, deeper analysis methods have opened doors to new assistive technologies, such as coaching systems, serious games, and tutoring systems, as well as diagnostic aids (e.g., for early detection of autism spectrum disorders, Alzheimer’s or Parkinson’s diseases). Tutoring systems, for example, have opened up new opportunities for voice professionals, such as public speakers, singers, and teachers, providing them with feedback on prosodic aspects, vibrato parameters, “presence” or quality. Further, methods of speech/voice enhancement and conversion have enabled improvements in intelligibility of spoken content, as well as socio-emotional communication skills of e.g., speakers on the autism spectrum. In this light and given the steadily growing research activities and their importance, we openly invite papers describing various aspects of analysis and synthesis of atypical speech and voices as well as their successful applications. Submissions must not have been previously published and must have specific connection to audio, speech, and music processing. Topics of interest include: * Automatic Recognition of Atypical Speech & Voice Patterns * Analysis of Atypical Speech, Singing & Voices * Robustness in Automatic Speech Recognition against Atypical Phenomena * Synthesis of Atypical Speech, Singing & Voices * Enhancement and Conversion for Intelligibility Improvement of Atypical Speech & Voices * Resources of Atypical Speech, Singing or Voice Patterns * Multimodal Integration for Atypical Speech & Voice Processing (e.g., videolaryngoscopy, videokymography, fMRI, etc.) * Tutoring Systems for Atypical Speech & Voice * Serious Gaming Approaches in Atypical Speech & Voices * Relationship Between Atypical Speech & Voices and Neurological Conditions Lead Guest Editor: * Björn W. Schuller, Imperial College London, London, U.K. & TUM, Munich, Germany Guest Editors: * Tiago H. Falk, INRS-EMT, Montreal, Canada * Vijay Parsa, University of Western Canada, London, Canada * Elmar Nöth, FAU Erlangen-Nuremberg, Germany & King Abdulaziz University, Jeddah, Saudi Arabia For more information about this special issue, please visit: http://si.eurasip.org/issues/16/atypical-speech-voices-corpora-classification/

Top

Call for Papers - 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:

◦   Full paper submission: 31^st March 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

Top

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)

Top

CALL FOR PAPERS

                                  Extended submission deadline 20 March 2014

TIPA: Travaux interdisciplinaires sur la parole et le langage
http://tipa.revues.org/

The 30^th issue of the TIPA journal is to appear in December 2014, on the following topic:

PROMINENCES and SPOKEN LANGUAGE

Invited editor: Sophie Herment, Laboratoire Parole et Langage, Aix-Marseille Université

works on speech and language. Articles dealing with prominences and spoken language will be welcome.

We invite submissions based on various backgrounds and linguistic fields: prosody, phonetics, phonology, syntax, morphology, pragmatics, dialectology, diachrony.

The term prominence encompasses many different meanings which will hopefully be dealt with in the various contributions. In spoken language, prominences can range from emphasis, focalisation, pitch accents, metric entities such as strong syllables or strong feet, etc.

Articles dealing with interfaces will also be of great interest: how are syntactic prominences realized in the spoken language? How is information structure related to prominence? Are certain morphological constituents more prominent than others? etc.

Papers building on different perspectives will be considered: corpus-based approaches, theoretical linguistics, psycholinguistics, neurolinguistics, automatic language processing, sociolinguistics, language teaching...

These aspects are by no means exhaustive, and all related issues or approaches that can shed light on the topic will be considered.

The language of publication will be either English or French. Each article should contain a detailed two-page abstract in the other language, in order to make papers in French more accessible to English-speaking readers, and vice versa, thus insuring a larger audience for all the articles.

Important dates:

February 29: deadline for abstract submission

March 30: notification of acceptance

June 30: deadline for submission of articles

December: publication.

Submission guidelines:

Please send your proposal in 2 files to: tipa@lpl-aix.fr

- one in .doc containing the title, name and affiliation of the author(s).

- the other anonymous in .pdf: it should not be longer than one A4 page (in times 12) and contain: the title; ½ page introducing the subject of the research and the theoretical / methodological framework; ½ page accounting for the main results. This one-page abstract can be followed by a short bibliography (5 or 6 titles; the author(s) of the proposal should not appear more than twice).

Instructions for authors can be found at http://www.lpl.univ-aix.fr/index.php?id=27

Top

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)

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 highquality 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, transaural and binaural 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)

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)

Top

Third Call for Papers - 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:

◦              Full paper submission: 31^st March 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

Top