Technical Program

ASR-1: Speech Recognition 1

Session Type: Poster
Poster Time: Wednesday, December 14, 10:30 - 12:30
Location: Lahaina Bay Room
Session Chair: Karen Livescu, Toyota Technological Institute, Chicago
 
ASR-1.1: I-VECTOR ESTIMATION AS AUXILIARY TASK FOR MULTI-TASK LEARNING BASED ACOUSTIC MODELING FOR AUTOMATIC SPEECH RECOGNITION
         Gueorgui Pironkov; University of Mons, Belgium
         Stephane Dupont; University of Mons, Belgium
         Thierry Dutoit; University of Mons, Belgium
 
ASR-1.2: BBN TECHNOLOGIES' OPENSAD SYSTEM
         Scott Novotney; Raytheon BBN Technologies, United States
         Damianos Karakos; Raytheon BBN Technologies, United States
         Jan Silovsky; Raytheon BBN Technologies, United States
         Rich Schwartz; Raytheon BBN Technologies, United States
 
ASR-1.3: A STUDY OF SPEECH DISTORTION CONDITIONS IN REAL SCENARIOS FOR SPEECH PROCESSING APPLICATIONS
         Dayana Ribas; Advanced Technologies Application Center (CENATAV), Cuba
         Emmanuel Vincent; Institute for Research in Computer Science and Automation (INRIA), France
         Jose R. Calvo; Advanced Technologies Application Center (CENATAV), Cuba
 
ASR-1.4: AUTOMATIC OPTIMIZATION OF DATA PERTURBATION DISTRIBUTIONS FOR MULTI-STYLE TRAINING IN SPEECH RECOGNITION
         Mortaza Doulaty; The University of Sheffield, United Kingdom
         Richard Rose; Google Inc., United States
         Olivier Siohan; Google Inc., United States
 
ASR-1.5: BATCH-NORMALIZED JOINT TRAINING FOR DNN-BASED DISTANT SPEECH RECOGNITION
         Mirco Ravanelli; Fondazione Bruno Kessler, Italy
         Philemon Brakel; University of Montreal, Canada
         Maurizio Omologo; Fondazione Bruno Kessler, Italy
         Yoshua Bengio; University of Montreal, Canada
 
ASR-1.6: DEEP BOTTLENECK FEATURES AND SOUND-DEPENDENT I-VECTORS FOR SIMULTANEOUS RECOGNITION OF SPEECH AND ENVIRONMENTAL SOUNDS
         Sakriani Sakti; Nara Institute of Science and Technology, Japan
         Seiji Kawanishi; Nara Institute of Science and Technology, Japan
         Graham Neubig; Nara Institute of Science and Technology, Japan
         Koichiro Yoshino; Nara Institute of Science and Technology, Japan
         Satoshi Nakamura; Nara Institute of Science and Technology, Japan
 
ASR-1.7: LEARNING UTTERANCE-LEVEL NORMALISATION USING VARIATIONAL AUTOENCODERS FOR ROBUST AUTOMATIC SPEECH RECOGNITION
         Shawn Tan; National University of Singapore, Singapore
         Khe Chai Sim; Google Inc., Singapore
 
ASR-1.8: PERFORMANCE MONITORING FOR AUTOMATIC SPEECH RECOGNITION IN NOISY MULTI-CHANNEL ENVIRONMENTS
         Bernd T. Meyer; Johns Hopkins University, United States
         Sri Harish Mallidi; Johns Hopkins University, United States
         Angel Mario Castro Martínez; Carl von Ossietzky Universität Oldenburg, Germany
         Guillermo Paya-Vaya; Leibniz Universität Hannover, Germany
         Hendrik Kayser; Carl von Ossietzky Universität Oldenburg, Germany
         Hynek Hermansky; Johns Hopkins University, United States
 
ASR-1.9: ITERATIVE TRAINING OF A DPGMM-HMM ACOUSTIC UNIT RECOGNIZER IN A ZERO RESOURCE SCENARIO
         Michael Heck; Nara Institute of Science and Technology, Japan
         Sakriani Sakti; Nara Institute of Science and Technology, Japan
         Satoshi Nakamura; Nara Institute of Science and Technology, Japan
 
ASR-1.10: TOWARD HUMAN-ASSISTED LEXICAL UNIT DISCOVERY WITHOUT TEXT RESOURCES
         Chris Bartels; SRI International, United States
         Wen Wang; SRI International, United States
         Vikramjit Mitra; SRI International, United States
         Colleen Richey; SRI International, United States
         Andreas Kathol; SRI International, United States
         Dimitra Vergyri; SRI International, United States
         Harry Bratt; SRI International, United States
         Chiachi Hung; SRI International, United States
 
ASR-1.11: A NONPARAMETRIC BAYESIAN APPROACH FOR AUTOMATIC DISCOVERY OF A LEXICON AND ACOUSTIC UNITS
         Amir Hossein Harati Nejad Torbati; Jibo Inc, United States
         Joseph Picone; Temple University, United States
 
ASR-1.12: JOINTLY LEARNING TO ALIGN AND CONVERT GRAPHEMES TO PHONEMES WITH NEURAL ATTENTION MODELS
         Shubham Toshniwal; Toyota Technological Institute at Chicago, United States
         Karen Livescu; Toyota Technological Institute at Chicago, United States