Publications
* denotes equal contribution
Please see my Google Scholar for the most up-to-date list of publications.
2024
- NAACL
- arXiv
2021
- ICASSPTransformer Based Unsupervised Pre-Training for Acoustic Representation LearningIn IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021, 2021
- InterSpeechDidispeech: A Large Scale Mandarin Speech CorpusIn IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021, 2021
2020
- InterSpeechTMT: A Transformer-Based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-Aware DialogIn 21st Annual Conference of the International Speech Communication Association, Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020, 2020
2019
2018
- ISCSLPComparable Study Of Modeling Units For End-To-End Mandarin Speech RecognitionIn 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018, Taipei City, Taiwan, November 26-29, 2018, 2018
- ISCSLPAn Analysis of Decoding for Attention-Based End-to-End Mandarin Speech RecognitionIn 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018, Taipei City, Taiwan, November 26-29, 2018, 2018
- arxivTowards End-to-End Code-Switching Speech RecognitionCoRR, 2018