Technical Program

M3: Automatic Speech Recognition II

Session Type: Poster
Poster Time: Monday, December 14, 15:30 - 17:00
Location: Earth + Air + Fire
Session Chair: Antti-Veikko Rosti, Apple Inc.
 
M3.1: INVESTIGATING SPARSE DEEP NEURAL NETWORKS FOR SPEECH RECOGNITION
         Gueorgui Pironkov; University of Mons, Belgium
         St├ęphane Dupont; University of Mons, Belgium
         Thierry Dutoit; University of Mons, Belgium
 
M3.2: LATENT DIRICHLET ALLOCATION BASED ORGANISATION OF BROADCAST MEDIA ARCHIVES FOR DEEP NEURAL NETWORK ADAPTATION
         Mortaza Doulaty; University of Sheffield, United Kingdom
         Oscar Saz; University of Sheffield, United Kingdom
         Raymond W. M. Ng; University of Sheffield, United Kingdom
         Thomas Hain; University of Sheffield, United Kingdom
 
M3.3: TOWARDS STRUCTURED DEEP NEURAL NETWORK FOR AUTOMATIC SPEECH RECOGNITION
         Yi-Hsiu Liao; Graduate Institute of Electronic Engineering, National Taiwan University, Taiwan
         Hung-Yi Lee; Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan
         Lin-shan Lee; Graduate Institute of Electronic Engineering, National Taiwan University, Taiwan
 
M3.4: LEARNING FACTORIZED FEATURE TRANSFORMS FOR SPEAKER NORMALIZATION
         Lahiru Samarakoon; National University of Singapore, Singapore
         Khe Chai SIM; National University of Singapore, Singapore
 
M3.5: IMPROVING DATA SELECTION FOR LOW-RESOURCE STT AND KWS
         Thiago Fraga da Silva; Vocapia Research, France
         Antoine Laurent; Vocapia Research, France
         Jean-Luc Gauvain; CNRS-LIMSI, France
         Lori Lamel; CNRS-LIMSI, France
         Viet Bac Le; Vocapia Research, France
         Abdel Messaoudi; Vocapia Research, France
 
M3.6: STRUCTURED DISCRIMINATIVE MODELS USING DEEP NEURAL-NETWORK FEATURES
         Rogier van Dalen; University of Cambridge, United Kingdom
         Jingzhou Yang; University of Cambridge, United Kingdom
         Haipeng Wang; University of Cambridge, United Kingdom
         Anton Ragni; University of Cambridge, United Kingdom
         Chao Zhang; University of Cambridge, United Kingdom
         Mark J. F. Gales; University of Cambridge, United Kingdom
 
M3.7: EESEN: END-TO-END SPEECH RECOGNITION USING DEEP RNN MODELS AND WFST-BASED DECODING
         Yajie Miao; Carnegie Mellon University, United States
         Mohammad Gowayyed; Carnegie Mellon University, United States
         Florian Metze; Carnegie Mellon University, United States
 
M3.8: STOCHASTIC GRADIENT VARIATIONAL BAYES FOR DEEP LEARNING-BASED ASR
         Andros Tjandra; Universitas Indonesia, Indonesia
         Sakriani Sakti; Nara Institute of Science and Technology, Japan
         Satoshi Nakamura; Nara Institute of Science and Technology, Japan
         Mirna Adriani; Universitas Indonesia, Indonesia
 
M3.9: INVESTIGATION OF BACK-OFF BASED INTERPOLATION BETWEEN RECURRENT NEURAL NETWORK AND N-GRAM LANGUAGE MODELS
         Xie Chen; Cambridge University, United Kingdom
         Xunying Liu; Cambridge University, United Kingdom
         Mark J. F. Gales; Cambridge University, United Kingdom
         Philip C. Woodland; Cambridge University, United Kingdom
 
M3.10: LSTM TIME AND FREQUENCY RECURRENCE FOR AUTOMATIC SPEECH RECOGNITION
         Jinyu Li; Microsoft, United States
         Abdel-Rahman Mohamed; Microsoft, United States
         Geoffrey Zweig; Microsoft, United States
         Yifan Gong; Microsoft, United States