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-22: Speech Recognition 8: Multilingual Speech Recognition

Session Type: Poster
Time: Wednesday, 9 June, 15:30 - 16:15
Location: Gather.Town
Session Chair: Karen Livescu, TTI-Chicago
 
SPE-22.1: CODE-SWITCH SPEECH RESCORING WITH MONOLINGUAL DATA
         Guoyu Liu; Tencent
         Lixin Cao; Tencent
 
SPE-22.2: MIXTURE OF INFORMED EXPERTS FOR MULTILINGUAL SPEECH RECOGNITION
         Neeraj Gaur; Google Inc.
         Brian Farris; Google Inc.
         Parisa Haghani; Google Inc.
         Isabel Leal; Google Inc.
         Pedro J. Moreno; Google Inc.
         Manasa Prasad; Google Inc.
         Bhuvana Ramabhadran; Google Inc.
         Yun Zhu; Google Inc.
 
SPE-22.3: REDUCING SPELLING INCONSISTENCIES IN CODE-SWITCHING ASR USING CONTEXTUALIZED CTC LOSS
         Burin Naowarat; Chulalongkorn University
         Thananchai Kongthaworn; Chulalongkorn University
         Korrawe Karunratanakul; ETH Zurich
         Sheng Hui Wu; NewEra AI Robotics
         Ekapol Chuangsuwanich; Chulalongkorn University
 
SPE-22.4: MULTI-DIALECT SPEECH RECOGNITION IN ENGLISH USING ATTENTION ON ENSEMBLE OF EXPERTS
         Amit Das; Microsoft
         Kshitiz Kumar; Microsoft
         Jian Wu; Microsoft
 
SPE-22.5: DECOUPLING PRONUNCIATION AND LANGUAGE FOR END-TO-END CODE-SWITCHING AUTOMATIC SPEECH RECOGNITION
         Shuai Zhang; School of Artificial Intelligence, University of Chinese Academy of Sciences
         Jiangyan Yi; Institute of Automation, Chinese Academy of Sciences
         Zhengkun Tian; School of Artificial Intelligence, University of Chinese Academy of Sciences
         Ye Bai; School of Artificial Intelligence, University of Chinese Academy of Sciences
         Jianhua Tao; School of Artificial Intelligence, University of Chinese Academy of Sciences
         Zhengqi Wen; School of Artificial Intelligence, University of Chinese Academy of Sciences
 
SPE-22.6: AISPEECH-SJTU ACCENT IDENTIFICATION SYSTEM FOR THE ACCENTED ENGLISH SPEECH RECOGNITION CHALLENGE
         Houjun Huang; AISpeech Ltd, Suzhou
         Xu Xiang; AISpeech Ltd, Suzhou
         Yexin Yang; Shanghai Jiao Tong University
         Rao Ma; Shanghai Jiao Tong University
         Yanmin Qian; Shanghai Jiao Tong University