2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

SPE-2: Speech Recognition 2: Neural transducer Models 2

Session Type: Poster
Time: Tuesday, 8 June, 13:00 - 13:45
Location: Gather.Town
 
SPE-2.1: ADVANCING RNN TRANSDUCER TECHNOLOGY FOR SPEECH RECOGNITION
         George Saon; IBM Research AI
         Zoltan Tueske; IBM Research AI
         Daniel Bolanos; IBM Research AI
         Brian Kingsbury; IBM Research AI
 
SPE-2.2: LESS IS MORE: IMPROVED RNN-T DECODING USING LIMITED LABEL CONTEXT AND PATH MERGING
         Rohit Prabhavalkar; Google
         Yanzhang He; Google
         David Rybach; Google
         Sean Campbell; Google
         Arun Narayanan; Google
         Trevor Strohman; Google
         Tara N. Sainath; Google
 
SPE-2.3: SIMPLEFLAT: A SIMPLE WHOLE-NETWORK PRE-TRAINING APPROACH FOR RNN TRANSDUCER-BASED END-TO-END SPEECH RECOGNITION
         Takafumi Moriya; NTT Corporation
         Takanori Ashihara; NTT Corporation
         Tomohiro Tanaka; NTT Corporation
         Tsubasa Ochiai; NTT Corporation
         Hiroshi Sato; NTT Corporation
         Atsushi Ando; NTT Corporation
         Yusuke Ijima; NTT Corporation
         Ryo Masumura; NTT Corporation
         Yusuke Shinohara; NTT Corporation
 
SPE-2.4: ECHO STATE SPEECH RECOGNITION
         Harsh Shrivastava; Georgia Institute of Technology
         Ankush Garg; Google
         Yuan Cao; Google
         Yu Zhang; Google
         Tara N. Sainath; Google
 
SPE-2.5: USING SYNTHETIC AUDIO TO IMPROVE THE RECOGNITION OF OUT-OF-VOCABULARY WORDS IN END-TO-END ASR SYSTEMS
         Xianrui Zheng; University of Cambridge
         Yulan Liu; Amazon
         Deniz Gunceler; Amazon
         Daniel Willett; Amazon