Technical Program

ZRS.1: The Zero Resource Speech Challenge 2017

Session Type: Poster
Poster Time: Monday, December 18, 11:00 - 12:30
Location: Poster Area
Session Chair: Tomoki Toda, Nagoya University
 
ZRS.1.1: AN EMBEDDED SEGMENTAL K-MEANS MODEL FOR UNSUPERVISED SEGMENTATION AND CLUSTERING OF SPEECH
         Herman Kamper; Stellenbosch University, South Africa
         Karen Livescu; Toyota Technological Institute at Chicago, United States
         Sharon Goldwater; University of Edinburgh, United Kingdom
 
ZRS.1.2: MULTILINGUAL BOTTLE-NECK FEATURE LEARNING FROM UNTRANSCRIBED SPEECH
         Hongjie Chen; Northwestern Polytechnical University, China
         Cheung-Chi Leung; Institute for Infocomm Research, A*STAR, Singapore
         Lei Xie; Northwestern Polytechnical University, China
         Bin Ma; Institute for Infocomm Research, A*STAR, Singapore
         Haizhou Li; National University of Singapore, Singapore
 
ZRS.1.3: EXTRACTING BOTTLENECK FEATURES AND WORD-LIKE PAIRS FROM UNTRANSCRIBED SPEECH FOR FEATURE REPRESENTATION
         Yougen Yuan; Northwestern Polytechnical University, China
         Cheung-Chi Leung; Institute for Infocomm Research, A*STAR, Singapore
         Lei Xie; Northwestern Polytechnical University, China
         Hongjie Chen; Northwestern Polytechnical University, China
         Bin Ma; Institute for Infocomm Research, A*STAR, Singapore
         Haizhou Li; National University of Singapore, Singapore
 
ZRS.1.4: FEATURE OPTIMIZED DPGMM CLUSTERING FOR UNSUPERVISED SUBWORD MODELING: A CONTRIBUTION TO ZEROSPEECH 2017
         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
 
ZRS.1.5: COMPOSITE EMBEDDING SYSTEMS FOR ZEROSPEECH2017 TRACK1
         Hayato Shibata; Tokyo Institute of Technology, Japan
         Taku Kato; Tokyo Institute of Technology, Japan
         Takahiro Shinozaki; Tokyo Institute of Technology, Japan
         Shinji Watanabe; Johns Hopkins University, United States
 
ZRS.1.6: DEEP LEARNING METHODS FOR UNSUPERVISED ACOUSTIC MODELING - LEAP SUBMISSION TO ZEROSPEECH CHALLENGE 2017
         Ansari TK; Indian Institute of Science, India
         Rajath Kumar; Indian Institute of Science, India
         Sonali Singh; Indian Institute of Science, India
         Sriram Ganapathy; Indian Institute of Science, India
 
ZRS.1.7: UNSUPERVISED HMM POSTERIOGRAMS FOR LANGUAGE INDEPENDENT ACOUSTIC MODELING IN ZERO RESOURCE CONDITIONS
         Ansari TK; Indian Institute of Science, India
         Rajath Kumar; Indian Institute of Science, India
         Sonali Singh; Indian Institute of Science, India
         Sriram Ganapathy; Indian Institute of Science, India
         Susheela Devi; Indian Institute of Science, India
 

Sponsors

Technical Sponsor