[Last update: 2023-Sept]
I am currently a speech recognition researcher and engineer at ByteDance.
I was a postdoc researcher in Multimedia Computing Group, Delft University of Technology (TU Delft) since during 2019 ~ 2021, working with Dr. Odette Scharenborg. I had worked in a collaborative research project with a group owned by Prof. Mark Hasegawa-Johnson (University of Illinois Urbana-Champaign) and a group owned by Prof. Najim Dehak (Johns Hopkins University), between 2020 and 2021.
I obtained the Ph.D. degree in Department of Electronic Engineering, The Chinese University of Hong Kong (CUHK), in 2020. My Ph.D advisor is Prof. Tan Lee. I started my Ph.D. Programme since 2015. I obtained the B.Eng. in Department of Electronic Engineering, Tsinghua University, Beijing, China in 2015.
My research interests include automatic speech recognition (ASR), low-resource/zero-resource speech modeling and inclusive ASR.
My CV (not up-to-date).
10-Sep 2023: My Journal paper "Towards inclusive automatic speech recognition" got accepted by Computer Speech and Language. It is an extended version of the arxiv pre-print: "Quantifying bias in automatic speech recognition".
30-May-2023: Two papers got accepted to INTERSPEECH 2023: "Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition" and "Language-universal Phonetic Encoder for Low-resource Speech Recognition".
2-June 2021: My paper accepted to INTERSPEECH 2021.
22-Apr 2021: My paper accepted for publication in IEEE Open Journal of Signal Processing.
2-Apr 2021: My two papers submitted to INTERSPEECH 2021: one for unsupervised acoustic unit discovery, the other for quantifying bias in ASR.
30-Jan 2021: My paper accepted to ICASSP 2021; A collaborative work with Xinsheng Wang accepted to ICASSP 2021.
25-July 2020: My paper accepted to INTERSPEECH 2020.
6-Mar 2020: I have successfully defended my Ph.D. Thesis.
25-January 2020: The joint work with Zhiyuan Peng on speech representation learning accepted to ICASSP 2020 as a poster presentation.
15-September 2019: I am attending INTERSPEECH 2019 at Graz, Austria, to give two oral presentations.
8-August 2019: My Journal manuscript "Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling" accepted for publication in Transactions on Audio, Speech and Language Processing (Trans. ASLP). Preprint available here.
31-July 2019: I will be visiting Prof. Hung-yi Lee's Lab at Department of Electrical Engineering, National Taiwan University, as a research exchange student for 2 weeks.
13-July 2019: I am giving a talk to M.Sc. students in CUHK(SZ). The title of my talk is "Unsupervised acoustic modeling for less-studied languages".
17-Jun 2019: My 2 papers accepted to INTERSPEECH 2019: ArXiv preprint of ZeroSpeech 2019 Challenge in a special session, and unsupervised acoustic modeling as an oral presentation.
12-May 2019: I am attending IEEE ICASSP 2019 at Brighton, UK, to give a poster presentation about language Identification.
25-Mar 2019: Our team achieved the second place (among 19 challenge submissions) in Zero Resource Speech Challenge (ZeroSpeech) 2019, ABX subword discriminability task!
1-Feb 2019: The joint work with Zhiyuan Peng on language identification accepted to IEEE ICASSP 2019.
2-Sep 2018: I am attending INTERSPEECH 2018 at Hyderabad, India, to give an oral and two poster presentations.
8-Aug 2018: The joint work with Yuanyuan Liu and Ying Qin on disordered speech assessment accepted to ISCSLP 2018 as an oral presentation.
7-Aug 2018: The joint work with Man-Ling Sung on unsupervised spoken pattern discovery accepted to APSIPA-ASC 2018 as an oral presentation.
4-Jun 2018: My 2 papers accepted to INTERSPEECH 2018: Unsupervised acoustic modeling as an oral presentation, and cross-lingual acoustic modeling as a poster presentation. The joint work with Ying Qin on Aphasic speech assessment is also accepted as a poster presentation.
2015-2020, Ph.D. in Electronic Engineering
The Chinese University of Hong Kong, Hong Kong S.A.R. of China
2011-2015, B.Eng in Electronics Information Engineering
Tsinghua University, Beijing, China
2021-now, Researcher and engineer
ByteDance
2019-2021, Postdoctoral researcher
Delft University of Technology, Delft, The Netherlands
Or, you may also find them from Google Scholar, or DBLP.
Machine Intelligence - Principles and Applications (TECS 2461, for selected outstanding Hong Kong middle school students). Teaching Assistant with Prof Tan Lee and Prof Hongsheng Li.
18-19 Sem 2
Introduction to Digital Signal Processing (ELEG 3503, for undergraduates of CUHK). Teaching Assistant with Prof. Tan Lee
18-19 Sem 1
Hong Kong Primary & Secondary Schools STEM Robotics Competition 2018. Organizer and Tutor
17-18 Sem 1 & 2
Digital Processing of Speech Signals (ELEG 5741, for postgraduates of CUHK). Teaching Assistant with Prof. Tan Lee
16-17 Sem 1
Signals and Systems (ENGG 2030, for undergraduates of CUHK). Teaching Assistant with Prof. Tan Lee
15-16 Sem 1
16-17 Sem 1
Digital Signal Processing and Applications (ELEG 4501, for undergraduates of CUHK). Teaching Assistant with Prof. Tan Lee
15-16 Sem 2
16-17 Sem 2