Programme

The detailed programme follows below with links to papers and presentations (where available).

9:00	Opening/Welcome
9:10	Overview of CHiME Challenge including summary of results
9:50	Oral session 1: challenge papers
10:40	Break
11:00	Oral session 2: challenge papers
12:15	Lunch break
13:45	Poster session
15:45	Break
16:00	Oral session 3: multisource event detection and classification
16:50	Plenary discussion: results and future evaluations
17:50	Closing

Detailed Programme

Introduction

• Opening Remarks [View Slides: pdf]
  Jon Barker (University of Sheffield, UK), Emmanuel Vincent (INRIA, Rennes, France)
• Overview of the PASCAL CHiME Speech Separation and Recognition Challenge [View Slides: pdf]
  Jon Barker (University of Sheffield, UK), Emmanuel Vincent (INRIA, Rennes, France), Ning Ma (University of Sheffield, UK), Heidi Christensen (University of Sheffield, UK) and Phil Green (University of Sheffield, UK),

Oral session 1

Session Chair: Phil Green, University of Sheffield

• Exemplar-Based Recognition of Speech in Highly Variable Noise [View Slides: pdf]
  Antti Hurmalainen, Katariina Mahkonen (Tampere University of Technology, Finland), Jort F. Gemmeke (Katholieke Universiteit Leuven, Belgium), and Tuomas Virtanen (Tampere University of Technology, Finland)
• CHIME Challenge: Approaches to Robustness using Beamforming and Uncertainty-of-Observation Techniques [View Slides: pdf, ppt]
  Dorothea Kolossa (Ruhr University Bochum, Germany), Ramon Fernandez Astudillo, Alberto Abad (INESC-ID, Portugal), Steffen Zeiler (Ruhr University Bochum, Germany), Rahim Saeidi (University of Eastern Finland), Pejman Mowlaee (Ruhr University Bochum, Germany), Joao Paulo da Silva Neto (INESC-ID, Portugal), and Rainer Martin (Ruhr University Bochum, Germany)

Oral session 2

Session Chair: Reinhold Häb-Umbach, University of Paderborn

• Speech Recognition in the Presence of Highly Non-Stationary Noise Based on Spatial, Spectral and Temporal Speech/Noise Modeling Combined with Dynamic Variance Adaptation [View Slides: pdf]
  Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Atsunori Ogawa, Takaaki Hori, Shinji Watanabe, Masakiyo Fujimoto, Takuya Yoshioka, Takanobu Oba, Yotaro Kubo, Mehrez Souden, Seong-Jun Hahm, and Atsushi Nakamura (NTT Communication Science Labs, Japan)
• Robust Automatic Speech Recognition through On-line Semi-Blind Source Extraction [View Slides: pdf]
  Francesco Nesta and Marco Matassoni (Fondazione Bruno Kessler-irst, Italy)
• The Munich 2011 CHiME Challenge Contribution: NMF-BLSTM Speech Enhancement and Recognition for Reverberated Multisource Environments [View Slides: pdf]
  Felix Weninger, Jürgen Geiger, Martin Wöllmer, Björn Schuller, and Gerhard Rigoll (Technische Universität München, Germany)

Oral session 3

Session Chair: Hiroshi Okuno, Kyoto University

• GMM-Based Classification from Noisy Features [View Slides: pdf]
  Alexey Ozerov (INRIA, Rennes, France), Mathieu Lagrange (STMS Lab IRCAM - CNRS - UPMC, France), and Emmanuel Vincent (INRIA, Rennes, France)
• Sound Event Detection in Multisource Environments Using Source Separation [View Slides: pdf]
  Toni Heittola, Annamaria Mesaros, Tuomas Virtanen (Tampere University of Technology, Finland), and Antti Eronen (Nokia Research Center, Finland)

Poster session

1. A Two-Channel Acoustic Front-End for Robust Automatic Speech Recognition in Noisy and Reverberant Environments
   Roland Maas, Andreas Schwarz, Yuanhang Zheng, Klaus Reindl, Stefan Meier, Armin Sehr, and Walter Kellermann (University of Erlangen-Nuremberg, Germany)
2. CHiME Data Separation Based on Target Signal Cancellation and Noise Masking
   Zbynek Koldovsky, Jiri Malek, Jan Nouza (TU Liberec, Czech Republic), and Miroslav Balik (VUT Brno, Czech Republic)
3. Designing Multimodal Acoustic Environment Corpus to Improve Speech Interaction in Living Room Kenichi Shibata, Kengo Ikeya, Yuki Deguchi, Yoichi Takebayashi, Shigeyoshi Kitazawa, Shinya Kiriyama (Shizuoka University, Japan)
4. Exemplar-Based Speech Enhancement and its Application to Noise-Robust Automatic Speech Recognition
   Jort F. Gemmeke (Katholieke Universiteit Leuven, Belgium), Tuomas Virtanen, and Antti Hurmalainen (Tampere University of Technology, Finland)
5. Mask Estimation and Sparse Imputation for Missing Data Speech Recognition in Multisource Reverberant Environments
   Heikki Kallasjoki (Aalto SCI, Finland), Sami Keronen (Aalto University School of Science, Finland), Guy J. Brown (University of Sheffield, UK), Jort F. Gemmeke (Katholieke Universiteit Leuven, Belgium), Ulpu Remes, and Kalle J. Palomäki (Aalto University School of Science, Finland)
6. Multi-layer Collaborative Microphone Array Beamforming in Presence of Nonstationary Interfering Signals
   Danilo Comminiello, Michele Scarpiniti, Raffaele Parisi (Sapienza University of Rome, Italy), Albenzio Cirillo, Mauro Falcone (Fondazione Ugo Bordoni, Italy), and Aurelio Uncini (Sapienza University of Rome, Italy)
7. Recent Advances in Fragment-Based Speech Recognition in Reverberant Multisource Environments
   Ning Ma, Jon Barker, Heidi Christensen, Phil Green (University of Sheffield, UK)
8. Robust Speech Recognition in Multi-Source Noise Environments using Convolutive Non-Negative Matrix Factorization
   Ravichander Vipperla, Simon Bozonnet, Dong Wang, and Nicholas Evans (EURECOM, France)
9. Source Separation using the Spectral Flatness Measure
   Rolf Bardeli (Fraunhofer IAIS, Germany)
10. Using the FASST Source Separation Toolbox for Noise Robust Speech Recognition
    Alexey Ozerov and Emmanuel Vincent (INRIA, Rennes, France)