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-14: Speech Recognition 6: New Algorithms for Sparsity/Efficiency

Session Type: Poster
Time: Wednesday, 9 June, 13:00 - 13:45
Location: Gather.Town
Session Chair: Bhuvana Ramabhadran, Google, Inc.
 
SPE-14.1: FASTEMIT: LOW-LATENCY STREAMING ASR WITH SEQUENCE-LEVEL EMISSION REGULARIZATION
         Jiahui Yu; Google Brain
         Chung-Cheng Chiu; Google Brain
         Bo Li; Google LLC
         Shuo-yiin Chang; Google LLC
         Tara N. Sainath; Google LLC
         Yanzhang He; Google LLC
         Arun Narayanan; Google LLC
         Wei Han; Google Brain
         Anmol Gulati; Google Brain
         Yonghui Wu; Google Brain
         Ruoming Pang; Google Brain
 
SPE-14.2: SPARSIFICATION VIA COMPRESSED SENSING FOR AUTOMATIC SPEECH RECOGNITION
         Kai Zhen; Indiana University Bloomington
         Hieu Nguyen; Amazon
         Feng-Ju Chang; Amazon
         Athanasios Mouchtaris; Amazon
         Ariya Rastrow; Amazon
 
SPE-14.3: DYNAMIC SPARSITY NEURAL NETWORKS FOR AUTOMATIC SPEECH RECOGNITION
         Zhaofeng Wu; University of Washington
         Ding Zhao; Google
         Qiao Liang; Google
         Jiahui Yu; Google
         Anmol Gulati; Google
         Ruoming Pang; Google
 
SPE-14.4: AN ASYNCHRONOUS WFST-BASED DECODER FOR AUTOMATIC SPEECH RECOGNITION
         Hang Lv; Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, China and Center of Language and Speech Processing, Johns Hopkins University
         Zhehuai Chen; Center of Language and Speech Processing at Johns Hopkins University, USA; SpeechLab, Departement of Computer Science and Engineering, Shanghai Jiao Tong University
         Hainan Xu; Center for Language Speech Processing at Johns Hopkins University
         Daniel Povey; Xiaomi Corporation
         Lei Xie; Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University
         Sanjeev Khudanpur; Center for Language Speech Processing at Johns Hopkins University and Human Language Technology Center of Excellence at Johns Hopkins University
 
SPE-14.5: TINY TRANSDUCER: A HIGHLY-EFFICIENT SPEECH RECOGNITION MODEL ON EDGE DEVICES
         Yuekai Zhang; Johns Hopkins University
         Sining Sun; Tencent Technology Co.,Ltd
         Long Ma; Tencent Technology Co.,Ltd
 
SPE-14.6: ONLINE AUTOMATIC SPEECH RECOGNITION WITH LISTEN, ATTEND AND SPELL MODEL
         Roger Hsiao; Apple Inc
         Dogan Can; Apple Inc
         Tim Ng; Apple Inc
         Ruchir Travadi; Apple Inc
         Arnab Ghoshal; Apple Inc