I am a speech scientist and technologist. My goal as a researcher is to build machine intelligence in making sense of audio, speech, and language information. This leads me to a number of subfields of computer science and electrical engineering, including infocomm, information science, machine learning, artificial intelligence, and multimedia processing. As a speech technologist, I believe in social value creation using human language technologies to deliver high-value-added solutions to people and society. As an educator, I see myself as a facilitator of learning, passionate about co-creating knowledge with students by building on their insights and curiosity to cultivate a collaborative and forward-looking learning environment.
My research interests are in spoken language analysis and generation, ranging from speaker recognition and anonymization, language and accent recognition, speech recognition and synthesis, diarization, voice biometrics spoofing and countermeasure. My research centers around the theme of using AI and technology to improve productivity and our daily life (a.k.a. use-inspired basic research), while acknowledging the importance of making AI accessible and explainable is the way moving forward.
Short Bio
I began my career as a research scientist at the Institute for Infocomm Research, A*STAR, Singapore, focusing on speaker and language recognition research. During my tenure there, I advanced to the roles of a team leader and later as a strategic planning manager. From 2018 to 2020, I worked at NEC Corporation in Japan, specializing in voice biometrics and multi-modal biometrics research. I had the privilege of working with an exceptional team on the voice biometrics feature of the NEC Bio-Idiom platform [NEC Technical Journal Vol. 13 No. 2]. In July 2020, I returned to Singapore to lead the Para-linguistic AI Group at the Institute for Infocomm Research, serving as Senior Scientist and Principal Investigator. I also briefly held the position of Associate Professor at the Singapore Institute of Technology (SIT) from March to September/October 2023. Currently, I am an Associate Professor at The Hong Kong Polytechnic University in Hong Kong. I also serve as an Editor for Elsevier Computer Speech and Language (since 2016), Senior AE for IEEE Signal Processing Letters (since 2024), and was an Associate Editor for IEEE/ACM Transactions on Audio, Speech and Language Processing (2017 - 2021), elected member of IEEE Speech and Language Processing Technical Committee (2019 - 2021, 2022 - 2024).
Extramural Activities
Chair (2025 - 2027) ISCA Speaker and Language Recognition (SpLC) SIG
Perspective and Panel Session Chairs APSIPA ASC, 2025, Singapore
Technical Program Co-Chair (2024) IEEE Spoken Language Technology (SLT) Workshop, 2024, Macao.
Senior AE (2024 - present) IEEE Signal Processing Letters
Technical Program Chair (2022) International Symposium on Chinese Spoken Language Processing (ISCSLP), 2022, Singapore.
Virtual Conference Chair (2022) IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2022, Singapore
Area Chair (2021) IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2021, Toronto
Technical Program Co-Chair (2021) IEEE Spoken and Language Technology (SLT) Workshop 2021, China
General Chair (2020) Speaker Odyssey 2020: Speaker and Language Recognition Workshop, Tokyo, Japan
Elected member (2019 – 2021, 2022 – 2024) IEEE Speech and Language Technical Committee
Associate Editor (2017 – 2021) IEEE/ACM Transactions on Audio, Speech, and Language Processing
Editor (2016 – present) Elsevier Computer Speech and Language
Award and Honors
2024 Gold Award, PREMIA Best Student Paper Awards 2024 (with Tianchi Liu), PREMIA, Singapore
2023 Best Paper Award (with Tianchi Liu), 2023 International Doctorate Forum, Hong Kong
2023 Top 3% Paper Recognition, IEEE ICASSP 2023, Rhodes Island, Greece
2021 CRF (Used-Inspired Basic Research) Award, A*STAR, Singapore
2020 Outstanding Service Award, IEEE ICME 2020, London, UK
2019 Outstanding Achievement Award, NEC Corporation, Japan
2015 Ganesh N. Ramaswamy Memorial Award (with Sven Shepstone), IEEE ICASSP 2015, Brisbane, Australia
2014 Ganesh N. Ramaswamy Memorial Award (with Liping Chen), IEEE ICASSP 2014, Florence, Italy
2013 Prestigious Engineering Achievement Award, Institution of Engineers, Singapore
Invited Talks and Lectures
Invited Talk, Privacy and Security in Spoken Language Technologies, Wuhan University of Technology, Wuhan, China, June 2025.
Keynote speech, Uncertainty in Speaker Representation: Exploring the Xi-vector Approach, The Greater Bay Area Speech and Language Processing Forum, CUHK (Shenzhen), November 2024.
Invited Talk, Uncertainty in Speaker Recognition: What it Represents and How to Handle it, Frontier Forum on Intelligence Speech Analysis and Generation, Hefei, China, July 2024.
Plenary Talk, Voice, Privacy and Adversary, Joint Workshop of VoicePersonae and ASVspoof, Tokyo, Japan, Nov 2023.
Invited Talk, Find Your Major: Voice/Speech Processing, IEEE Tokyo Section Young Professionals & Educational Activities, Aug 2022
Expert Panel, Beyond Words: Recognition, Spoofing, and Anonymization of Individual Traits in Speech, ICASSP 2022, Singapore, May 2022
Plenary Talk, Recent Trends and Challenges in Speaker Recognition, International Conference on Asian Language Processing, Singapore, Dec, 2021
Invited Talk, Speech AI - My Voice Tells You Who I am and More, Wutong Forum, CUHK (Shenzhen), China, August 14, 2021
Keynote talk, Embedding in Speaker Recognition and Recent Advances, Spoken Language Interaction for Mobile Transportation System Workshop, Kunshan, China, Oct 2020
Tutorial lecture, Speaker Recognition: Fundamentals to Practice, Speech Science and Technology Conference, Sydney, Australia, Dec 2018
Invited lecture, Factor Analysis for Speaker Recognition, Summer School on Machine Learning, University of Eastern Finland, Finland, Aug 2017