SPE-10: Speech Recognition 4: Transformer Models 2 |
Session Type: Poster |
Time: Tuesday, 8 June, 16:30 - 17:15 |
Location: Gather.Town |
Virtual Session: View on Virtual Platform |
Session Chair: Yangyang Shi, Facebook AI |
SPE-10.1: CASS-NAT: CTC ALIGNMENT-BASED SINGLE STEP NON-AUTOREGRESSIVE TRANSFORMER FOR SPEECH RECOGNITION |
Ruchao Fan; University of California, Los Angeles |
Wei Chu; PAII Inc. |
Peng Chang; PAII Inc. |
Jing Xiao; PAII Inc. |
SPE-10.2: NON-AUTOREGRESSIVE TRANSFORMER ASR WITH CTC-ENHANCED DECODER INPUT |
Xingchen Song; Tsinghua University |
Zhiyong Wu; Tsinghua University |
Yiheng Huang; Tencent |
Chao Weng; Tencent |
Dan Su; Tencent |
Helen Meng; Chinese University of Hong Kong |
SPE-10.3: TRANSFORMER-BASED END-TO-END SPEECH RECOGNITION WITH LOCAL DENSE SYNTHESIZER ATTENTION |
Menglong Xu; Northwestern Polytechnical University |
Shengqiang Li; Northwestern Polytechnical University |
Xiao-Lei Zhang; Northwestern Polytechnical University |
SPE-10.4: DEVELOPING REAL-TIME STREAMING TRANSFORMER TRANSDUCER FOR SPEECH RECOGNITION ON LARGE-SCALE DATASET |
Xie Chen; Microsoft |
Yu Wu; Microsoft |
Zhenghao Wang; Microsoft |
Shujie Liu; Microsoft |
Jinyu Li; Microsoft |
SPE-10.5: HEAD-SYNCHRONOUS DECODING FOR TRANSFORMER-BASED STREAMING ASR |
Mohan Li; Toshiba Cambridge Research Laboratory |
Cătălin Zorilă; Toshiba Cambridge Research Laboratory |
Rama Doddipatla; Toshiba Cambridge Research Laboratory |
SPE-10.6: HISTORY UTTERANCE EMBEDDING TRANSFORMER LM FOR SPEECH RECOGNITION |
Keqi Deng; Institute of Acoustics, Chinese Academy of Sciences |
Gaofeng Cheng; Institute of Acoustics, Chinese Academy of Sciences |
Haoran Miao; Institute of Acoustics, Chinese Academy of Sciences |
Pengyuan Zhang; Institute of Acoustics, Chinese Academy of Sciences |
Yonghong Yan; Institute of Acoustics, Chinese Academy of Sciences |