Monday May 12
9:00      Registration
9:45      Opening remarks
9:55      Keynote 1 – Tao Zhang (video)
10:55    Break
11:25    Oral session 1 – Advances in sparse modeling and low-rank modeling for speech processing
12:45    Lunch
14:00    Poster / demo session 1
16:00    Break
16:30    RoSP SIG meeting / Free time
17:10    Walk to Remicourt Castle (18th century)
17:30    Welcome reception and French games

Tuesday May 13
9:15      Keynote 2 – Marc Moonen (slides)
10:15    Break
10:45    Oral session 2 – Microphone array processing
12:45    Lunch
14:00    Poster / demo session 2
16:00    Break
16:30    Oral session 3 – Multichannel speech processing in domestic environments
17:30    Move to Stanislas square / Pass by hotel
18:30    Mystery hunt through the Renaissance town
20:00    Banquet in the Great Hall of Nancy City Hall (18th century) – Awards ceremony

Wednesday May 14
9:15      Keynote 3 – Steve Renals (videoslides)
10:15    Break
10:45    Oral session 4 – Robust ASR
12:25    Closing remarks
12:30    Lunch

Keynote 1 (chair: Emmanuel Vincent)
Tao Zhang (Starkey Hearing Technologies, USA) (video)
Signal processing research for hearing aids: a practical perspective

Oral session 1 (chair: Afsaneh Asaei)
Advances in sparse modeling and low-rank modeling for speech processing

  • Mohammad J. Taghizadeh, Afsaneh Asaei, Philip N. Garner, Herve Bourlard (Idiap Research Institute, Switzerland)
    Ad-hoc microphone array calibration from partial distance measurements
    Nominated for best student paper award
  • Zhuo Chen (Columbia University, USA), Hélène Papadopoulos (Laboratoire des Signaux et Systèmes, France), Daniel P. W. Ellis (Columbia University, USA)
    Content-adaptive speech enhancement by sparsely-activated dictionary plus low rank decomposition
  • Antoine Liutkus (Inria, France), Zafar Rafii, Bryan Pardo (Northwestern University, USA), Derry FitzGerald (Dublin Institute of Technology, Ireland), Laurent Daudet (Université Paris Diderot, France)
    Kernel spectrogram models for source separation
  • Pablo Sprechmann (Duke University, USA), Alex Bronstein (Tel Aviv University, Israel), Guillermo Sapiro (Duke University, USA)
    Supervised non-Euclidean sparse NMF via bilevel optimization with applications to speech enhancement

Poster / demo session 1

  1. Jort Gemmeke (KU Leuven, Belgium)
    The self-taught vocal interface
  2. Ante Jukić (University of Oldenburg, Germany), Toon van Waterschoot (KU Leuven, Belgium), Timo Gerkmann, Simon Doclo (University of Oldenburg, Germany)
    Speech dereverberation with multi-channel linear prediction and sparse priors for the desired signal
  3. Nasser Mohammadiha, Simon Doclo (University of Oldenburg, Germany)
    Transient noise reduction using nonnegative matrix factorization
  4. Armin Saeb, Farbod Razzazi (Islamic Azad University, Iran), Massoud Babaie-Zadeh (Sharif University of Technology, Iran)
    A fast phoneme recognition system based on sparse representation of test utterances
  5. Syed Zubair, Wenwu Wang (University of Surrey, United Kingdom), Jonathon A. Chambers (Loughborough University, United Kingdom)
    Discriminative tensor dictionaries and sparsity for speaker identification
  6. Hai Morgenstern, Boaz Rafaely (Ben-Gurion University of the Negev, Israel)
    Far-field criterion for spherical microphone arrays and directional sources
  7. Jounghoon Beh, Dmitry Zotkin, Ramani Duraiswami (University of Maryland, USA)
    Adaptive interference rejection using generalized sidelobe canceller in spherical harmonics domain
  8. Gary W. Elko, Jens Meyer (mh Acoustics, USA)
    Adaptive beamformer for spherical eigenbeamforming microphone arrays
  9. Jiri Malek, David Botka, Zbynek Koldovsky (Technical University of Liberec, Czech Republic), Sharon Gannot (Bar-Ilan University, Israel)
    Methods to learn bank of filters steering nulls toward potential positions of a target source
  10. Daniele Giacobello, Jason Wung, Ramin Pichevar, Joshua Atkins (Beats Electronics, USA)
    Tuning methodology for speech enhancement algorithms using a simulated conversational database and perceptual objective measures
  11. Randy Gomez, Keisuke Nakamura, Takeshi Mizumoto, Kazuhiro Nakadai (Honda Research Institute, Japan)
    Improved hands-free automatic speech recognition in reverberant environment condition
  12. Mariem Bouafif and Zied Lachiri (National Engineering School of Tunis, Tunisia)
    Mixing parameters determination for multi-sources distance localization based on time delay of arrival
    Late-breaking poster
  13. Yann Salaün, Emmanuel Vincent (Inria, France), Nancy Bertin (CNRS, France), Nathan Souviraà-Labastie (Université Rennes 1, France), Xabier Jaureguiberry (Institut Mines-Télécom, France), Dung T. Tran (Inria, France), and Frédéric Bimbot (CNRS, France)
    The flexible audio source separation toolbox
    Late-breaking demo

Keynote 2 (chair: Walter Kellermann)
Marc Moonen (Electrical Engineering Department, KU Leuven, Belgium) (slides)
Distributed adaptive node-specific signal estimation in wireless acoustic sensor networks

Oral session 2 (chair: Gary Elko)
Microphone array processing

  • Yuval Dorfan, Gershon Hazan, Sharon Gannot (Bar-Ilan University, Israel)
    Multiple acoustic sources localization using distributed expectation-maximization algorithm
    Nominated for best student paper award
  • Michael Jeffet, Boaz Rafaely (Ben-Gurion University of the Negev, Israel)
    Study of a generalized spherical array beamformer with adjustable binaural reproduction
    Nominated for best student paper award
  • Lalan Kumar, Kushagra Singhal, Rajesh M. Hegde (Indian Institute of Technology Kanpur, India)
    Near-field source localization using spherical microphone array
  • Jonathan Blanchette, Martin Bouchard (University of Ottawa, Canada)
    Short-time multichannel noise correlation matrix estimators for acoustic signals
  • Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura (Nara Institute of Science and Technology, Japan), Yu Takahashi, Kazunobu Kondo (Yamaha Corporation, Japan), Hirokazu Kameoka (The University of Tokyo, Japan)
    Divergence optimization in nonnegative matrix factorization with spectrogram restoration for multichannel signal separation
  • Falk-Martin Hoffmann, Filippo M. Fazi (University of Southampton, United Kingdom)
    Circular microphone array with tangential pressure gradient sensors

Poster / demo session 2

  1. Craig Anderson (Victoria University, New Zealand), Stefan Meier, Walter Kellermann (University Erlangen-Nuremberg, Germany), Paul D. Teal (Victoria University, New Zealand), Mark Poletti (Industrial Research Ltd, New Zealand)
    A GPU-accelerated real-time implementation of TRINICON-BSS for multiple separation units
  2. Toru Taniguchi (Toshiba Corporation, Japan), Nobutaka Ono (National Institute of Informatics, Japan), Akinori Kawamura (Toshiba Corporation, Japan), Shigeki Sagayama (University of Tokyo, Japan)
    An auxiliary-function approach to online independent vector analysis for real-time blind source separation
  3. Leela Gudupudi (EURECOM, France), Christophe Beaugeant (Intel, France), Nicholas Evans (EURECOM, France), Moctar Mossi, Ludovick Lepauloux (Intel, France)
    A comparison of different loudspeaker models to empirically estimated non-linearities
  4. Miquel Espi, Masakiyo Fujimoto, Yotaro Kubo, Tomohiro Nakatani (NTT Corporation, Japan)
    Spectrogram patch based acoustic event detection and classification in speech overlapping conditions
  5. Shunsuke Nakai, Hiroshi Saruwatari, Ryoichi Miyazaki, Satoshi Nakamura (Nara Institute of Science and Technology, Japan), Kazunobu Kondo (Yamaha Corporation, Japan)
    Theoretical analysis of biased MMSE short-time spectral amplitude estimator and its extension to musical-noise-free speech enhancement
  6. Sebastian Stenzel, Juergen Freudenberger (University of Applied Sciences Konstanz, Germany), Gerhard Schmidt (CAU Kiel, Germany)
    A minimum variance beamformer for spatially distributed microphones using a soft reference selection
  7. Nilesh Madhu (NXP Software, Belgium), Rainer Martin (Ruhr-University Bochum, Germany), Heinz-Werner Rehn (Volkswagen AG, Germany), Sebastian Gergen (Ruhr-University Bochum, Germany), Andreas Fischer (Volkswagen AG, Germany)
    A hierarchical approach for the online, on-board detection and localisation of brake squeal using microphone arrays
  8. David Alon, Boaz Rafaely (Ben-Gurion University of the Negev, Israel)
    Spatial aliasing cancellation for circular microphone array
  9. Ankit Sohni, Chaitanya Ahuja, Rajesh M. Hegde (Indian Institute of Technology Kanpur, India)
    Extraction of pinna spectral notches in the median plane of a virtual spherical microphone array
  10. Vladimir Tourbabin, Boaz Rafaely (Ben-Gurion University of the Negev, Israel)
    Utilizing motion in humanoid robots to enhance spatial information recorded by microphone arrays
  11. Mikko Parviainen, Pasi Pertilä (Tampere University of Technology, Finland), Matti S Hämäläinen (Nokia Research Center, Finland)
    Self-localization of wireless acoustic sensors in meeting rooms
  12. Hendrik Barfuss and Walter Kellermann (University Erlangen-Nuremberg, Germany)
    Improving blind source separation performance by adaptive array geometries for humanoid robots
    Late-breaking poster

  13. Dmitry Zotkin, Jounghoon Beh (University of Maryland, USA), Adam O’Donovan (VisiSonics Corporation, USA), Ramani Duraiswami (University of Maryland, USA)
    Real-time construction and acoustic measurement via ad hoc microphone arrays
    Late-breaking demo
  14. Grégory Rump (Aldebaran Robotics, France)
    Embedded sound localization on a humanoid robot
    Late-breaking demo

Oral session 3 (chair: Maurizio Omologo)
Multichannel speech processing in domestic environments

  • Alessio Brutti, Mirco Ravanelli, Piergiorgio Svaizer, Maurizio Omologo (Fondazione Bruno Kessler, Italy)
    A speech event detection and localization task for multiroom environments
  • Yuuki Tachioka, Tomohiro Narita (Mitsubishi Electric Corporation, Japan), Shinji Watanabe, Jonathan Le Roux (Mitsubishi Electric Research Laboratories, USA)
    Ensemble integration of calibrated speaker localization and statistical speech detection in domestic environments
  • Panagiotis Giannoulis, Antigoni Tsiami, Isidoros Rodomagoulakis, Athanasios Katsamanis (National Technical University of Athens), Gerasimos Potamianos (University of Thessaly, Greece), Petros Maragos (National Technical University of Athens)
    The Athena-RC system for speech activity detection and speaker localization in the DIRHA smart home

Keynote 3 (chair: Mike Seltzer) (videoslides)
Steve Renals (School of Informatics, University of Edinburgh, United Kingdom)
Neural networks for distant speech recognition

Oral session 4 (chair: Shoji Makino)
Robust ASR

  • Armin Sehr (Beuth Hochschule für Technik Berlin, Germany), Hendrik Barfuss, Christian Hofmann, Roland Maas, Walter Kellermann (University of Erlangen-Nuremberg, Germany)
    Efficient training of acoustic models for reverberation-robust medium-vocabulary automatic speech recognition
  • Fine Aprilyanti, Hiroshi Saruwatari, Satoshi Nakamura (Nara Institute of Science and Technology, Japan), Tomoya Takatani (Toyota Motor Corporation, Japan)
    Optimized joint noise suppression and dereverberation based on blind signal extraction for hands-free speech recognition system
  • Cristina M. Guerrero, Maurizio Omologo (Fondazione Bruno Kessler, Italy)
    Word boundary agreement to combine multi-microphone hypotheses in distant speech recognition
  • Arseniy Gorin, Denis Jouvet, Emmanuel Vincent, Dung Tran (Inria, France)
    Investigating stranded GMM for improving automatic speech recognition
  • Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara (Kyoto University, Japan)
    Exploring deep neural networks and deep autoencoders in reverberant speech recognition