Workshop programme

The detailed programme follows below. More information on the keynote talks can be found here.

Monday 30 May

9:30 Opening/Welcome
9:40 Keynote 1
10:40 Break
11:10 Four talks of 15+5 minutes
12:30 Lunch
13:30 Poster spotlights
14:30 Break
15:00 Poster Session
17:30 End of Poster Session
18:00-19:30 Welcome Reception

Tuesday 31 May

9:30Keynote 2
10:30Break
11:10Four talks of 15+5 minutes
12:30 Lunch
13:30 Poster/Demo spotlights
14:30 Break
15:00 Poster/Demo Session
17:30 End of Poster/Demo Session
19:00 Conference dinner (The Caves)

Wednesday 1 June

9:30Keynote 3
10:30Break
11:00Three talks of 15+5 minutes
12:00Closing talk
12.40Closing remarks
12.40Lunch

Detailed Programme

Monday 30 May

Keynote 1

A Versatile Speech Front-End for Telecommunication and Speech Recognition - The Last One Mile : Implementation Issues for a Better Product
Akihiko Sugiyama (NEC Information and Media Processing Laboratories, Japan)

Talks 1 – Distant Speech Recognition

Channel Selection based on Multichannel Cross-Correlation Coefficients for Distant Speech Recognition
Kenichi Kumatani (Disney Research, Pittsburgh, USA); John McDonough, Jill Lehman, Bhiksha Raj (Carnegie Mellon University, USA)

Discriminative approach to dynamic variance adaptation for noisy speech recognition
Marc Delcroix, Shinji Watanabe, Tomohiro Nakatani, Atsushi Nakamura (NTT Communication Science Laboratories, Japan)

Extension of the REMOS Concept to Frequency-Filtering-Based Features for Reverberation-Robust Speech Recognition
Roland Maas (University of Erlangen-Nuremberg, Germany); Martin Wolf (Universitat Politècnica de Catalunya, Spain); Armin Sehr (University of Erlangen-Nuremberg, Germany); Climent Nadeu (UPC, Spain); Walter Kellermann (University Erlangen-Nuremberg, Germany)

Theoretical analysis of parametric blind spatial subtraction array and its application to speech recognition performance prediction
Ryoichi Miyazaki, Hiroshi Saruwatari, Ryo Wakisaka, Kiyohiro Shikano (Graduate School of Information Science, Nara Institute of Science and Technology, Japan); Tomoya Takatani (Toyota Motor Corporation, Japan)

Posters 1

Audio Spatio-Temporal Fingerprints for Cloudless Real-Time Hands-Free Diarization on Mobile Devices
Danil Korchagin (Idiap Research Institute, Switzerland)

Worst-case performance optimization for spherical microphone array modal beamformers
Haohai Sun (Norwegian University of Science and Technology, Norway), Shefeng Yan (Chinese Academy of Science, P.R. China), Ulf Peter Svensson (Norwegian University of Science and Technology, Norway)

Blind source separation of mixed speech in a high reverberation environment
Keiju Iso (University of Tsukuba, Japan), Shoko Araki (NTT Communication Science Laboratories, Japan), Shoji Makino (University of Tsukuba, Japan), Tomohiro Nakatani, Hiroshi Sawada (NTT communication Science Laboratories, Japan); Takeshi Yamada (University of Tsukuba, Japan), Atsushi Nakamura (NTT Communication Science Laboratories, Japan)

Diffuseness estimation via surface arrays for directional audio coding
Michael Meier, Giovanni Del Galdo (Fraunhofer Institute for Integrated Circuits IIS, Germany)

Median Tracking in Noise Subspace for Noise Floor Estimation
Mahdi Triki (Philips Research, The Netherlands)

Self-clustering non-Euclidean kernels for improving the estimation of multidimensional TDOA of multiple sources
Francesco Nesta, Alessio Brutti (Fondazione Bruno Kessler, Italy)

An Improved Combination of Directional BSS and a Source Localizer for Robust Source Separation in Rapidly Time-varying Acoustic Scenarios
Yuanhang Zheng, Anthony Lombard, Walter Kellermann (University Erlangen-Nuremberg, Germany)

Group Delay based methods for Speech Source Localization over Circular Arrays
Ardhendu Tripathy, Lalan Kumar, Rajesh M Hegde (IIT Kanpur, India)

Improving Hands-Free Speech Recognition in a Car Through Audio-Visual Voice Activity Detection
Friedrich Faubel, Munir Georges (Saarland University, Germany); Kenichi Kumatani (Disney Research, Pittsburgh, USA); Dietrich Klakow (Saarland University, Germany)

Sub-Nyquist Spatial Sampling Using Arrays of Directional Microphones
Vladimir Tourbabin, Boaz Rafaely (Ben-Gurion University, Israel)

Non-linear Spectro-temporal Modulations for Reverberant Speech Recognition
Marco Matassoni, Hari Krishna Maganti, Maurizio Omologo (Fondazione Bruno Kessler - irst, Italy)

A Time-domain Implementation of Data-Independent Robust Broadband Beamformers with Low Filter Order
Edwin Mabande (University of Erlangen-Nuremberg, Germany); Adrian Schad (Technology University of Darmstadt, Germany); Walter Kellermann (University Erlangen-Nuremberg, Germany)

Linearly constrained minimum variance method for spherical microphone arrays in a coherent environment
Yotam Peled, Boaz Rafaely (Ben-Gurion University, Israel)

An Integrated Framework for Multi-Channel Multi-Source Localization and Voice Activity Detection
Mohammad J. Taghizadeh, Philip Garner, Herve Bourlard (Idiap Research Institute, Switzerland); Hamid Reza Abutalebi (Yazd University, Iran); Afsaneh Asaei (Idiap Research Institute, Switzerland)

Combined Echo and Noise Reduction for Distributed Microphones
Eric Böhmler, Juergen Freudenberger, Sebastian Stenzel (University of Applied Sciences Constance, Germany)

Time-frequency masking for convolutive and noisy mixtures
Juergen Freudenberger, Sebastian Stenzel (University of Applied Sciences Constance, Germany)

Speech Measurements Using a Laser Doppler Vibrometer Sensor: Application to Speech Enhancement
Yekutiel Avargel (AudioZoom Ltd, Israel); Israel Cohen (Technion, Israel)

Tuesday 31 May

Keynote 2

Model-Based Approaches to Handling Additive Noise in Reverberant Environments
Mark Gales (University of Cambridge, UK)

Talks 2 – Microphone arrays

Towards Acoustic Self-Localization of Ad Hoc Smartphone Array
Marius Hennecke, Gernot Fink (TU Dortmund University, Germany)

A Wave-Domain Model for Acoustic MIMO Systems with Reduced Complexity
Martin Schneider, Walter Kellermann (University Erlangen-Nuremberg, Germany)

Closed-Form Self-Localization of Asynchronous Microphone Arrays
Pasi Pertilä, Mikael Mieskolainen (Tampere University of Technology, Finland); Matti S Hämäläinen (Nokia Research Center, Finland)

Dereverberation Performance of Rigid and Open Spherical Microphone Arrays: Theory & Simulation
Daniel P Jarrett (Imperial College London, United Kingdom); Emanuel Habets (International Audio Laboratories Erlangen, Germany); Mark Thomas, Nikolay D Gaubitch, Patrick A Naylor (Imperial College London, United Kingdom)

Posters 2

Use of reflected wavefronts for acoustic source localization with a line array
Piergiorgio Svaizer, Alessio Brutti, Maurizio Omologo (Fondazione Bruno Kessler - irst, Italy)

A Double Talk Control Method Improving Estimation Speed by Adjusting Required Error Level
Kensaku Fujii, Takuto Yoshioka, Kana Yamasaki(University of Hyogo, Japan); Mitsuji Muneyasu (Kansai University, Japan); Masakazu Morimoto (University of Hyogo, Japan)

First-order Superdirectional Acoustic Zooming in the Presence of Directional Interferences
Rene Derkx (Philips Research, Eindhoven, The Netherlands)

Functional Link Based Architectures For Nonlinear Acoustic Echo Cancellation
Danilo Comminiello (Sapienza University of Rome, Italy); Luis Azpicueta-Ruiz (Universidad Carlos III de Madrid, Spain); Michele Scarpiniti (University of Rome "La Sapienza", Italy); Aurelio Uncini (Univerity of Rome "La Sapienza", Italy); Jerónimo Arenas-García (Universidad Carlos III de Madrid, Spain)

Generating Virtual Microphone Signals Using Geometrical Information Gathered by Distributed Arrays
Giovanni Del Galdo, Oliver Thiergart, Tobias Weller (Fraunhofer Institute for Integrated Circuits IIS, Germany); Emanuel Habets (International Audio Laboratories Erlangen, Germany)

Joint Dereverberation and Noise Reduction Using a Two-Stage Beamforming Approach
Emanuel Habets (International Audio Laboratories Erlangen, Germany); Jacob Benesty (INRS-EMT, University of Quebec, Canada)

Multi-Style Training of HMMs with Stereo Data for Reverberation-Robust Speech Recognition
Armin Sehr, Christian Hofmann, Roland Maas, Walter Kellermann (University Erlangen-Nuremberg, Germany)

A critical Analysis of nonstationary Variance Estimates in the Maximum Negentropy Beamformer
Barbara Rauch, Friedrich Faubel, Dietrich Klakow (Saarland University, Germany)

Incorporating localisation cues in a fragment decoding framework for distant binaural speech recognition
Ning Ma, Jon Barker, Heidi Christensen, Phil Green (University of Sheffield, United Kingdom)

Demos

Low-latency meeting recognition and understanding using distant microphones
Shoko Araki, Takaaki Hori, Takuya Yoshioka, Masakiyo Fujimoto, Shinji Watanabe, Takanobu Oba, Atsunori Ogawa, Kazuhiro Otsuka, Dan Mikami, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Atsushi Nakamura, Junji Yamato (NTT Communication Science Laboratories, Japan)

A Speech-Based Conversation System for Accessing Agriculture Commodity Prices in Indian Languages
Gautam Varma Mantena, Rajendran S., Rambabu B., Suryakanth Gangashetty, Yegnanarayana B., Kishore Prahallad (IIIT Hyderabad, India)

Positioning System for Mobile Terminals Using a Microphone Array Network as an Intuitive Interface
Shimpei Soda, Koji Kugata, Tomoya Takagi, Hiroki Noguchi, Shintaro Izumi, Masahiko Yoshimoto, Hiroshi Kawaguchi (Kobe University, Japan)

IllumiSense: Context Sensitive Illumination
Marius Hennecke, Christian Kleine-Cosack, Gernot Fink (TU Dortmund University, Germany)

A Practical Beamformer-Postfilter System for Adaptive Speech Enhancement in Non-Stationary Noise Environments
Tobias Wolff, Markus Buck (Nuance Communications, Germany)

Real-time prototype for multiple source tracking through Generalized State Coherence Transform and Particle Filtering
Francesco Nesta, Alessio Brutti, Luca Cristoforetti (Fondazione Bruno Kessler - irst, Italy)

The Ambient Spotlight: Personal meeting capture with a microphone array
Jonathan Kilgour, Jean Carletta, Steve Renals (University of Edinburgh, United Kingdom)

Wednesday 1 June

Keynote 3

Environmental sound recognition and classification
Dan Ellis (Columbia University, USA)

Talks 3 – Microphone arrays and applications

Statistical Method to Identify Key Anthropometric Parameters in HRTF Individualization
Mengqiu Zhang, Rodney Andrew Kennedy, Thushara D. Abhayapala (Australian National University, Australia); Wen Zhang (Process Science and Engineering, CSIRO, Australia)

A microphone array system integrating beamforming, feature enhancement, and spectral mask-based noise estimation
Takuya Yoshioka, Tomohiro Nakatani (NTT Corporation, Japan)

Single and Multichannel Enhancement of Distant Speech using characteristics of Speech Production
Yegnanarayana B., Guruprasad S (IIIT Hyderabad, India); Prasanna S r m (IIT Guwahati, India); Suryakanth Gangashetty (IIIT Hyderabad, India)

Closing Talk

HSCMA: Hands-free Sound Capture and Microphone Array in Kinect
Ivan Tashev (Microsoft Research, USA)