Technical Program

T2: 3rd CHiME Speech Separation and Recognition Challenge

Session Type: Poster
Poster Time: Tuesday, December 15, 11:00 - 12:30
Location: Earth + Air + Fire
Session Chair: Olivier Pietquin, Université Lille
 
T2.1: ADAPTIVE BEAMFORMING AND ADAPTIVE TRAINING OF DNN ACOUSTIC MODELS FOR ENHANCED MULTICHANNEL NOISY SPEECH RECOGNITION
         Alexey Prudnikov; Speech Technology Center Inc., Russian Federation
         Maxim Korenevsky; ITMO University, Russian Federation
         Sergei Aleinik; ITMO University, Russian Federation
 
T2.2: BOOSTED ACOUSTIC MODEL LEARNING AND HYPOTHESES RESCORING ON THE CHIME-3 TASK
         Shahab Jalalvand; University of Trento, Italy
         Daniele Falavigna; Fondazione Bruno Kessler, Italy
         Marco Matassoni; Fondazione Bruno Kessler, Italy
         Piergiorgio Svaizer; Fondazione Bruno Kessler, Italy
         Maurizio Omologo; Fondazione Bruno Kessler, Italy
 
T2.3: UNIFIED ASR SYSTEM USING LGM-BASED SOURCE SEPARATION, NOISE-ROBUST FEATURE EXTRACTION, AND WORD HYPOTHESIS SELECTION
         Yusuke Fujita; Hitachi, Ltd, Japan
         Ryoichi Takashima; Hitachi, Ltd, Japan
         Takeshi Homma; Hitachi, Ltd, Japan
         Rintaro Ikeshita; Hitachi, Ltd, Japan
         Yohei Kawaguchi; Hitachi, Ltd, Japan
         Takashi Sumiyoshi; Hitachi, Ltd, Japan
         Takashi Endo; Hitachi, Ltd, Japan
         Masahito Togami; Hitachi, Ltd, Japan
 
T2.4: SPEECH ENHANCEMENT USING BEAMFORMING AND NON NEGATIVE MATRIX FACTORIZATION FOR ROBUST SPEECH RECOGNITION IN THE CHIME-3 CHALLENGE
         Thanh T. Vu; Nanyang Technological University, Singapore
         Benjamin Bigot; Nanyang Technological University, Singapore
         Eng Siong Chng; Nanyang Technological University, Singapore
 
T2.5: AN INFORMATION FUSION APPROACH TO RECOGNIZING MICROPHONE ARRAY SPEECH IN THE CHIME-3 CHALLENGE BASED ON A DEEP LEARNING FRAMEWORK
         Jun Du; University of Science and Technology of China, China
         Qing Wang; University of Science and Technology of China, China
         Yan-Hui Tu; University of Science and Technology of China, China
         Xiao Bao; University of Science and Technology of China, China
         Li-Rong Dai; University of Science and Technology of China, China
         Chin-Hui Lee; Georgia Institute of Technology, United States
 
T2.6: THE NTT CHIME-3 SYSTEM: ADVANCES IN SPEECH ENHANCEMENT AND RECOGNITION FOR MOBILE MULTI-MICROPHONE DEVICES
         Takuya Yoshioka; NTT Corporation, Japan
         Nobutaka Ito; NTT Corporation, Japan
         Marc Delcroix; NTT Corporation, Japan
         Atsunori Ogawa; NTT Corporation, Japan
         Keisuke Kinoshita; NTT Corporation, Japan
         Masakiyo Fujimoto; NTT Corporation, Japan
         Chengzhu Yu; The University of Texas at Dallas, United States
         Wojciech Fabian; NTT Corporation, Japan
         Miquel Espi; NTT Corporation, Japan
         Takuya Higuchi; NTT Corporation, Japan
         Shoko Araki; NTT Corporation, Japan
         Tomohiro Nakatani; NTT Corporation, Japan
 
T2.7: BLSTM SUPPORTED GEV BEAMFORMER FRONT-END FOR THE 3RD CHIME CHALLENGE
         Jahn Heymann; University of Paderborn, Germany
         Lukas Drude; University of Paderborn, Germany
         Aleksej Chinaev; University of Paderborn, Germany
         Reinhold Haeb-Umbach; University of Paderborn, Germany
 
T2.8: MULTI-CHANNEL SPEECH PROCESSING ARCHITECTURES FOR NOISE ROBUST SPEECH RECOGNITION: 3RD CHIME CHALLENGE RESULTS
         Lukas Pfeifenberger; Graz University of Technology, Austria
         Tobias Schrank; Graz University of Technology, Austria
         Matthias Zöhrer; Graz University of Technology, Austria
         Martin Hagmüller; Graz University of Technology, Austria
         Franz Pernkopf; Graz University of Technology, Austria
 
T2.9: ROBUST SPEECH RECOGNITION USING BEAMFORMING WITH ADAPTIVE MICROPHONE GAINS AND MULTICHANNEL NOISE REDUCTION
         Shengkui Zhao; Advanced Digital Sciences Center, Singapore
         Xiong Xiao; Nanyang Technological University, Singapore
         Zhaofeng Zhang; Nagaoka University of Technology, Japan
         Thi Ngoc Tho Nguyen; Advanced Digital Sciences Center, Singapore
         Xionghu Zhong; Nanyang Technological University, Singapore
         Bo Ren; Nagaoka University of Technology, Japan
         Longbiao Wang; Nagaoka University of Technology, Japan
         Douglas L. Jones; Advanced Digital Sciences Center, Singapore
         Eng Siong Chng; Nanyang Technological University, Singapore
         Haizhou Li; Institute For Infocomm Research, Singapore
 
T2.10: A CHIME-3 CHALLENGE SYSTEM: LONG-TERM ACOUSTIC FEATURES FOR NOISE ROBUST AUTOMATIC SPEECH RECOGNITION
         Niko Moritz; Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Germany
         Stephan Gerlach; Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Germany
         Kamil Adiloglu; Hörtech gGmbH, Germany
         Jörn Anemüller; University of Oldenburg, Germany
         Birger Kollmeier; University of Oldenburg, Germany
         Stefan Goetze; Fraunhofer IDMT, Project Group for Hearing, Speech, and Audio Technology, Germany
 
T2.11: THE MERL/SRI SYSTEM FOR THE 3RD CHIME CHALLENGE USING BEAMFORMING, ROBUST FEATURE EXTRACTION, AND ADVANCED SPEECH RECOGNITION
         Takaaki Hori; Mitsubishi Electric Research Laboratories, United States
         Zhuo Chen; Columbia University, United States
         Hakan Erdogan; Sabanci University, Turkey
         John Hershey; Mitsubishi Electric Research Laboratories, United States
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories, United States
         Vikramjit Mitra; SRI International, United States
         Shinji Watanabe; Mitsubishi Electric Research Laboratories, United States
 
T2.12: ROBUST ASR USING NEURAL NETWORK BASED SPEECH ENHANCEMENT AND FEATURE SIMULATION
         Sunit Sivasankaran; INRIA, France
         Aditya Arie Nugraha; INRIA, France
         Emmanuel Vincent; INRIA, France
         Juan A. Morales-Cordovilla; INRIA, France
         Siddharth Dalmia; INRIA, France
         Irina Illina; INRIA, France
         Antoine Liutkus; INRIA, France
 
T2.13: EXPLOITING SYNCHRONY SPECTRA AND DEEP NEURAL NETWORKS FOR NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION
         Ning Ma; University of Sheffield, United Kingdom
         Ricard Marxer; University of Sheffield, United Kingdom
         Jon Barker; University of Sheffield, United Kingdom
         Guy J. Brown; University of Sheffield, United Kingdom
 
T2.14: COMBINING SPECTRAL FEATURE MAPPING AND MULTI-CHANNEL MODEL-BASED SOURCE SEPARATION FOR NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION
         Deblin Bagchi; The Ohio State University, United States
         Michael Mandel; The Ohio State University, United States
         Zhongqiu Wang; The Ohio State University, United States
         Yanzhang He; The Ohio State University, United States
         Andrew Plummer; The Ohio State University, United States
         Eric Fosler-Lussier; The Ohio State University, United States
 
T2.15: THE THIRD `CHIME' SPEECH SEPARATION AND RECOGNITION CHALLENGE: DATASET, TASK AND BASELINES
         Jon Barker; University of Sheffield, United Kingdom
         Ricard Marxer; University of Sheffield, United Kingdom
         Emmanuel Vincent; INRIA, France
         Shinji Watanabe; Mitsubishi Electric Research Laboratories, United States