I lead the Multimodal Generative AI Group and the AI for Education Programme at the Institute for Infocomm Research (I2R), Agency for Science, Technology, and Research (A*STAR), Singapore. I'm also a principal investigator at Centre for Frontier AI Research (CFAR), A*STAR.
My team advances conversational and multimodal intelligence, focusing on how AI systems understand, interact, and align with humans across languages, contexts, and societies. Our work bridges speech and language processing with real-world deployment, shaping the transition from data-driven models to socially grounded AI systems. Our technology has spawned multiple commercial spin-offs, and speech evaluation technology developed by my team has been deployed at the Ministry of Education, Singapore during the COVID-19 pandemic to help support home based learning and promote spoken language education (more details).
ISCA Fellow, AAIA Fellow, A*STAR Fellow. I have served as program chair for NeurIPS 2025 and ICLR 2023, IEEE SPS Distinguished Lecturer 2023. I received my PhD from MIT and Harvard. During my PhD, I worked at MIT Lincoln Laboratory on multilingual speech processing.
News, Media, and Talks
Keynote at LREC 2026
Advisory Board, IJCAI and ECAI 2026
2026 Invited talk at MBZUAI Speech and NLP Symposium, Abu Dhabi, UAE
2025 Embodied Agent Interface Challenge at NeurIPS, 2nd place
2025 NeurIPS Program Chair
2025 ISCA Fellow citation: For significant contributions and technical leadership in multilingual speech processing, multimodal human-machine communication, and AI technology deployment.
2025 Inducted Professional Member, IEEE Eta Kappa Nu (HKN) - IEEE honor society for top engineers
Feature in ELLE magazine, March 8 2025
Keynotes at Multimedia Modeling (MMM) 2025, ACPA 2025 [news], 2025 EMNLP CODI CRAC, O-COCOSDA 2025
Keynotes and panels at ICASSP 2024, Seoul, South Korea:
SeaEval For Multilingual and Multicultural Foundation Models: From Crosslingual Alignment to Cultural Reasoning, Self-supervision in Audio, Speech and Beyond (SASB) Workshop, April 14
Multimodal, Multilingual Conversational AI Technology for Enhancing Inclusivity in Education, Hands-free Speech Communication and Microphone Arrays (HSCMA) Workshop, April 15
Women in Signal Processing Luncheon, April 17
We are part of the AI Alliance led by IBM and Meta! [website] [news]
SeaEval Benchmark for Multicultural and Multilingual Foundation Models [website] [arxiv] [github]
Singapore's National LLM Program: Multimodal and Multilingual Foundation Models for Southeast Asian Context [news]
Our work in Advancing Education with Personalized LLMs in ZaoBao, 25 Dec 2023 [news in Chinese] [English translation]
Outstanding Paper Award at EMNLP 2023 [paper] [award announcement]
Inaugural A*STAR Fellow, 2023
Program Chair for ICLR 2023
2023 IEEE SPS Distinguished Lecturer [IEEE web announcement; IEEE Signal Processing Magazine Feature]
LLM Keynotes at ROCLING 2023, NLPMC@IJCNLP& AACL 2023, ACML 2023
Keynote Speaker at IMDA Technical Sharing #2 on Large Language Models, 29 Sep 2023 [video].
Keynote Speaker at Taming LLM Workshop@SIGDIAL & INLG 2023 on SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning, Prague, Czech Republic, 12 Sep 2023.
Keynote Speaker at SLaTE, ISCA-SIG on "Inclusive AI for Language Learning", Dublin, Ireland, 18 Aug 2023.
Cover Story of A*STAR Research: Talking Points, July 2023
Neural Language Generation: From Self-Supervised Representation Learning to Multimodal Contextualization, University of Texas at San Antonio, MATRIX AI Seminar Series (Special Feature), April 5, 2023
EVA: Education via AI, Artificial Intelligence Research Seminar (AIRS) Series, Singapore University of Technology and Design (SUTD), April 17, 2023
Neural Language Generation: From Self-Supervised Representation Learning to Multimodal Contextualization, Chinese University of Hong Kong (CUHK) School of Data Science (SDS) Colloquium Series, Mar 22, 2023
Neural Language Generation: From Self-Supervised Representation Learning to Multimodal Contextualization, IEEE Signal Processing Society Distinguished Lecture for Madras Section, Feb 22, 2023
Neural Language Generation: From Self-Supervised Representation Learning to Multimodal Contextualization, IEEE Signal Processing Society Distinguished Lecture for Student Branch at IIT-Kharagpur, Feb 17, 2023
Quoted in Asian Scientist "Language Models Running Wild", Nov 2, 2022
Survey Talk on "Summarizing Conversations: From Meetings to Social Media Chats", Interspeech 2022, Incheon, South Korea.
[photos] [video], Sep 19 2022Panelist, Challenges for Conversational AI: Semi-Supervised, Reinforced, and More, Workshop on Towards Semi-Supervised and Reinforced Task-Oriented Dialog Systems, EMNLP 2022
Panelist, Current Challenges and Advances in Multiparty Meeting and Dialogue Summarization, SummDial@SemDial 2022
Controllable Neural Language Generation, Plenary Talk at annual Frederick Jelinek Memorial Summer Workshop, Johns Hopkins University, Baltimore, USA, Aug 1 2022 (talk announcement, workshop link)
Data Science Education: The Signal Processing Perspective (Panel Discussion), ICASSP, Singapore, May 24 2022
Senior Area Chair, AACL 2022
EVA (Education via AI): Theoretical and Practical Considerations for Technology Deployment, AI Seminar Series, SEAB (Singapore Examination and Assessment Board), Apr 20 2022
Virtual Language Coaches Powered by Artificial Intelligence, GAIA STEM Lecture Series, Natioanl Central University, Taiwan, Feb 19 2022
Area Chair for ACL 2021, EMNLP 2021
Fast Prototyping a Dialogue Comprehension System, Ohio State University, Columbus, Ohio, USA, Mar 29 2021
Keynote speech at AI Singapore - Ministry of Education Workshop on AI for Mother Tongue Language Learning - Dec 2021
Understanding Clinical Conversations, Abridge AI Inc., (CMU spin-off), Pennsylvania, USA, Sep 2 2020
Singapore 100 Women in Tech 2021 [ citation, IMDA full honor list] [weblink] - Oct 2021
Election to ISCA Board [news link] - Sep 2021
Best Paper Award at SIGDIAL 2021
Young Scientist Best Paper Award at MICCAI 2021
Interview by Tamil Murasu on 20 September 2020 [news link] [English translation]
P&G Connect + Develop Open Innovation Award 2020
Moderator, Low Resource NLP Panel, SSNLP - Dec 2020
Thanks L’Oréal and UNESCO! L’Oréal Singapore For Women in Science National Fellowship 2019 [award announcement] [more info]
Invited Speaker, Lifelong Learning for Spoken Language Systems Workshop, IEEE ASRU - Dec 2019
Invited Speaker, Conversational AI: Data Augmentation, Dialogue Comprehension, Summary Generation, IPAL Singapore France Workshop - Dec 2019
Invited Speaker, Conversational AI: From Knowledge Representation to Spoken Dialogue Comprehension and Summarization, UBTech AI Forum - Nov 2019
Invited Speaker, Acoustic Signal Processing, Automatic Speech Recognition, and Machine Translation for Emotion Recognition and Analysis, Digital Emotions Seminar at A*STAR & ADSC - Mar 2019
Spoken Dialogue Comprehension and Summarization, National University of Singapore, Oct 2 2019
Seminar on Spoken Language Processing: Automatic Speech Recognition and Beyond, Singapore University of Technology and Design - Mar 2017
Low Resource Spoken Keyword Search, MIT Lincoln Lab, Boston, Massachusetts, USA, Sep 15 2016
Seminar on "Low Resource Spoken Keywoard Search" at JHU CSLP on 20 Sep 2016 [details]
Talk on Low Resource Spoken Keyword Search at IBM on 27 July 2015
Featured in Zao Bao (Singapore's Chinese Newspaper) on International Women’s Day on 8 March 2015
IEEE Signal Processing Singapore Chapter, Workshop on Natural Language Processing, Open Keyword Search for Low-Resource Spoken Languages - 16 December 2014
Seminar on Strategies for Spoken Keyword Search in Vietnamese, Academia Sinica, Taiwan on 10 Jan 2014
Seminar on Informative Dialect Recognition, National University of Singapore, 23 Aug 2012
Invited Talk, Consonant landmarks: automatic detection and interpretation, Ken Stevens Retirement: Quantal Transition, Acoustic Society of America, Miami, Florida, USA, Nov 2008
Seminar on Automatically Characterizing English Dialects using Phonological Rules, MGH Voice Research Forum, Boston, MA, USA, 31 Oct 2008