PW1: Robust Speech/Language Systems |
Session Type: Poster |
Poster Time: Wednesday, December 10, 10:00 - 11:30 |
Location: Emerald 4-6 |
Session Chair: Wilson Tam, SRI International
|
|
PW1.101: SYLLABLE BASED KEYWORD SEARCH: TRANSDUCING SYLLABLE LATTICES TO WORD LATTICES |
Hang Su; International Computer Science Institute, United States |
Jim Hieronymus; International Computer Science Institute, United States |
Yanzhang He; The Ohio State University, United States |
Eric Fosler-Lussier; The Ohio State University, United States |
Steven Wegmann; International Computer Science Institute, United States |
|
PW1.102: A WORD-LEVEL TOKEN-PASSING DECODER FOR SUBWORD N-GRAM LVCSR |
Matti Varjokallio; Aalto University, Finland |
Mikko Kurimo; Aalto University, Finland |
|
PW1.103: BUT ASR SYSTEM FOR BABEL SURPRISE EVALUATION 2014 |
Martin Karafiat; FIT BUT, Czech Republic |
Karel Vesely; FIT BUT, Czech Republic |
Igor Szoke; FIT BUT, Czech Republic |
Lukas Burget; FIT BUT, Czech Republic |
Frantisek Grezl; FIT BUT, Czech Republic |
Mirko Hannemann; FIT BUT, Czech Republic |
Jan Cernocky; FIT BUT, Czech Republic |
|
PW1.104: MULTICHANNEL FEATURE ENHANCEMENT IN DISTRIBUTED MICROPHONE ARRAYS FOR ROBUST DISTANT SPEECH RECOGNITION IN SMART ROOMS |
Seyedmahdad Mirsamadi; The University of Texas at Dallas, United States |
John H. L. Hansen; The University of Texas at Dallas, United States |
|
PW1.105: A SPARSITY BASED PREPROCESSING FOR NOISE ROBUST SPEECH RECOGNITION |
Christos Koniaris; University of Gothenburg, Sweden |
Saikat Chatterjee; KTH Royal Institute of Technology, Sweden |
|
PW1.106: EXEMPLAR-BASED NOISE ROBUST AUTOMATIC SPEECH RECOGNITION USING MODULATION SPECTROGRAM FEATURES |
Deepak Baby; KU Leuven, Belgium |
Tuomas Virtanen; Tampere University of Technology, Finland |
Jort Florent Gemmeke; KU Leuven, Belgium |
Tom Barker; Tampere University of Technology, Finland |
Hugo Van hamme; KU Leuven, Belgium |
|
PW1.107: A COMPLETE KALDI RECIPE FOR BUILDING ARABIC SPEECH RECOGNITION SYSTEMS |
Ahmed Ali; Qatar Computing Research Institute, Qatar |
Yifan Zhang; Qatar Computing Research Institute, Qatar |
Patrick Cardinal; MIT Computer Science and Artificial Intelligence Laboratory, United States |
Najim Dahak; MIT Computer Science and Artificial Intelligence Laboratory, United States Virgin Islands |
Stephan Vogel; Qatar Computing Research Institute, Qatar |
James Glass; MIT Computer Science and Artificial Intelligence Laboratory, United States |
|
PW1.108: A KEYWORD SEARCH SYSTEM USING OPEN SOURCE SOFTWARE |
Jan Trmal; University of Johns Hopkins, United States |
Guoguo Chen; University of Johns Hopkins, United States |
Daniel Povey; University of Johns Hopkins, United States |
Sanjeev Khudanpur; University of Johns Hopkins, United States |
Pegah Ghahremani; University of Johns Hopkins, United States |
Xiaohui Zhang; University of Johns Hopkins, United States |
Vimal Manohar; University of Johns Hopkins, United States |
Chunxi Liu; University of Johns Hopkins, United States |
Aren Jansen; University of Johns Hopkins, United States |
Dietrich Klakow; Saarland University, Germany |
David Yarowsky; University of Johns Hopkins, United States |
Florian Metze; Carnegie Mellon University, United States |
|
PW1.109: ONLINE WORD-SPOTTING IN CONTINUOUS SPEECH WITH RECURRENT NEURAL NETWORKS |
Pallavi Baljekar; Carnegie Mellon University, Disney Research Pittsburgh, United States |
Jill Fain Lehman; Disney Research Pittsburgh, United States |
Rita Singh; Carnegie Mellon University,Disney Research Pittsburgh, United States |
|
PW1.110: VARIABLE-ACTIVATION AND VARIABLE-INPUT DEEP NEURAL NETWORK FOR ROBUST SPEECH RECOGNITION |
Rui Zhao; Microsoft, China |
Jinyu Li; Microsoft, United States |
Yifan Gong; Microsoft, United States |
|
PW1.111: DEEP CONVOLUTIONAL NETS AND ROBUST FEATURES FOR REVERBERATION-ROBUST SPEECH RECOGNITION |
Vikramjit Mitra; SRI, United States |
Wen Wang; SRI, United States |
Horacio Franco; SRI, United States |
|