SPE-48: Speech Recognition 18: Low Resource ASR |
Session Type: Poster |
Time: Friday, 11 June, 11:30 - 12:15 |
Location: Gather.Town |
Virtual Session: View on Virtual Platform |
Session Chair: Shinji Watanabe, Johns Hopkins University |
SPE-48.1: MIXSPEECH: DATA AUGMENTATION FOR LOW-RESOURCE AUTOMATIC SPEECH RECOGNITION |
Linghui Meng; Institute of Automation, Chinese Academy of Sciences |
Jin Xu; Institute for Interdisciplinary Information Sciences, Tsinghua University |
Xu Tan; Microsoft Research Asia |
Jindong Wang; Microsoft Research Asia |
Tao Qin; Microsoft Research Asia |
Bo Xu; Institute of Automation, Chinese Academy of Sciences |
SPE-48.2: END-TO-END MULTILINGUAL AUTOMATIC SPEECH RECOGNITION FOR LESS-RESOURCED LANGUAGES: THE CASE OF FOUR ETHIOPIAN LANGUAGES |
Solomon Teferra Abate; Addis Ababa University |
Martha Yifiru Tachbelie; Addis Ababa University |
Tanja Schultz; University of Bremen |
SPE-48.3: IMPROVED DATA SELECTION FOR DOMAIN ADAPTATION IN ASR |
Shannon Wotherspoon; Raytheon BBN |
William Hartmann; Raytheon BBN |
Matthew Snover; Raytheon BBN |
Owen Kimball; Raytheon BBN |
SPE-48.4: BI-APC: BIDIRECTIONAL AUTOREGRESSIVE PREDICTIVE CODING FOR UNSUPERVISED PRE-TRAINING AND ITS APPLICATION TO CHILDREN’S ASR |
Ruchao Fan; University of California, Los Angeles |
Amber Afshan; University of California, Los Angeles |
Abeer Alwan; University of California, Los Angeles |
SPE-48.5: META-ADAPTER: EFFICIENT CROSS-LINGUAL ADAPTATION WITH META-LEARNING |
Wenxin Hou; Tokyo Institute of Technology |
Yidong Wang; Tokyo Institute of Technology |
Shengzhou Gao; Tokyo Institute of Technology |
Takahiro Shinozaki; Tokyo Institute of Technology |
SPE-48.6: ERROR-DRIVEN FIXED-BUDGET ASR PERSONALIZATION FOR ACCENTED SPEAKERS |
Abhijeet Awasthi; IIT Bombay |
Aman Kansal; IIT Bombay |
Sunita Sarawagi; IIT Bombay |
Preethi Jyothi; IIT Bombay |