Technical Program

ADV.1: ASR in Adverse Environments

Session Type: Poster
Poster Time: Wednesday, December 20, 11:00 - 12:30
Location: Poster Area
Session Chair: Marc Delcroix, NTT Corporation
 
ADV.1.1: NOISE-ROBUST EXEMPLAR MATCHING FOR RESCORING QUERY-BY-EXAMPLE SEARCH
         Emre Yilmaz; Radboud University, Netherlands
         Julien van Hout; SRI International, United States
         Horacio Franco; SRI International, United States
 
ADV.1.2: LEARNING SPEAKER REPRESENTATION FOR NEURAL NETWORK BASED MULTICHANNEL SPEAKER EXTRACTION
         Katerina Zmolikova; Brno University of Technology, Czech Republic
         Marc Delcroix; NTT, Japan
         Keisuke Kinoshita; NTT, Japan
         Takuya Higuchi; NTT, Japan
         Atsunori Ogawa; NTT, Japan
         Tomohiro Nakatani; NTT, Japan
 
ADV.1.3: UNSUPERVISED DOMAIN ADAPTATION FOR ROBUST SPEECH RECOGNITION VIA VARIATIONAL AUTOENCODER-BASED DATA AUGMENTATION
         Wei-Ning Hsu; Massachusetts Institute of Technology, United States
         Yu Zhang; Massachusetts Institute of Technology, United States
         James Glass; Massachusetts Institute of Technology, United States
 
ADV.1.4: BINAURAL PROCESSING FOR ROBUST RECOGNITION OF DEGRADED SPEECH
         Anjali Menon; Carnegie Mellon University, United States
         Chanwoo Kim; Google Inc., United States
         Umpei Kurokawa; Carnegie Mellon University, United States
         Richard Stern; Carnegie Mellon University, United States
 
ADV.1.5: MEETING RECOGNITION WITH ASYNCHRONOUS DISTRIBUTED MICROPHONE ARRAY
         Shoko Araki; NTT, Japan
         Nobutaka Ono; National Institute of Informatics, Japan
         Keisuke Kinoshita; NTT, Japan
         Marc Delcroix; NTT, Japan
 
ADV.1.6: ADVERSARIAL TRAINING FOR DATA-DRIVEN SPEECH ENHANCEMENT WITHOUT PARALLEL CORPUS
         Takuya Higuchi; NTT, Japan
         Keisuke Kinoshita; NTT, Japan
         Marc Delcroix; NTT, Japan
         Tomohiro Nakatani; NTT, Japan
 
ADV.1.7: TACKLING UNSEEN ACOUSTIC CONDITIONS IN QUERY-BY-EXAMPLE SEARCH USING TIME AND FREQUENCY CONVOLUTION FOR MULTILINGUAL DEEP BOTTLENECK FEATURES
         Julien van Hout; SRI International, United States
         Vikramjit Mitra; SRI International, United States
         Horacio Franco; SRI International, United States
         Chris Bartels; SRI International, United States
         Dimitra Vergyri; SRI International, United States
 
ADV.1.8: IMPROVING SEPARATION OF OVERLAPPED SPEECH FOR MEETING CONVERSATIONS USING UNCALIBRATED MICROPHONE ARRAY
         Keisuke Nakamura; Honda Research Institute Japan Co., Ltd., Japan
         Randy Gomez; Honda Research Institute Japan Co., Ltd., Japan
 

Sponsors

Technical Sponsor