Technical Program

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