Liming Wang (汪黎明)

lmwang@se.cuhk.edu.hk

I'm an Assistant Professor in the Department of Systems Engineering and Engineering Management at The Chinese University of Hong Kong. Previously, I was a postdoctoral associate at the spoken language system group of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). Prior to that, I did my PhD at the University of Illinois Urbana-Champaign (UIUC), advised by Mark Hasegawa-Johnson. I am the recipient of Robert T. Chien Memorial Award for Electrical Engineering (2023) and Rambus Computer Engineering Fellowship (2020) for my research.

PhD opening for Fall 2027: I am considering applications for one additional PhD student, subject to research fit, funding availability, and the departmental admission process.

Research focus: I am primarily seeking candidates with strong experience or demonstrated interest in speech and audio processing, speech/audio foundation models, multimodal language modeling, or multimodal healthcare AI.

How to apply: Please email me your CV, transcript, intended starting date, and a brief description of your previous research contributions and the research questions you would like to pursue.

Because my supervision capacity is limited, I may only be able to respond to candidates whose backgrounds closely match my current projects.

CV  /  Scholar  /  LinkedIn  /  Github

profile photo

Research

Current research interest includes:

  • Statistical learning theory for multimodal learning
  • Multimodal learning with unpaired modalities
  • Multimodal compositional representation learning
  • Generative models
* denotes equal contribution.

CALM:Class-Conditional Sparse Attention Vectors for Large Audio-Language Models
Videet Mehta, Liming Wang, Hilde Kuehne, Rogerio Feris, James R. Glass, M. Jehanzeb Mirza Videet Mehta, Liming Wang, Hilde Kuehne, Rogerio Feris, Muhammad Jehanzeb Mirza, James Glass
EMNLP, 2026  
project page / arXiv

Unsupervised Speech Recognition at the Syllable Level
Liming Wang, Junrui Ni, Kai-Wei Chang, David Harwath, MarkHasegawa-Johnson, James Glass
EMNLP, 2026  
project page / arXiv

Can Diffusion Models Disentangle? A Theoretical Perspective
Liming Wang, Muhammad Jehanzeb Mirza, Yishu Gong, Yuan Gong, Jiaqi Zhang, Brian Tracey, Katerina Placek, Marco Vilela, James Glass
NeurIPS, 2025  
project page / arXiv

Recognizing Dementia from Neuropsychological Tests with State Space Models
Liming Wang, Saurabhchand Bhati, Cody Karjadi, Rhoda Au, James Glass
ASRU, 2025  
project page / arXiv

Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer
Liming Wang, Yuan Gong, Nauman Dawalatabad, Marco Vilela, Katerina Placek, Brian Tracey, Yishu Gong, Fernando Vieira, James Glass
Interspeech, 2024  
project page / arXiv

Towards Unsupervised Speech Recognition without Pronunciation Models
Junrui Ni, Liming Wang, Yang Zhang, Kaizhi Qian, Heting Gao, Mark Hasegawa-Johnson, Chang D. Yoo
Speech Communication, 2025  
project page / arXiv



Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching
Liming Wang, Mark Hasegawa-Johnson, Chang D. Yoo
International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024  
project page / arXiv

A Theory of Unsupervised Speech Recognition
Liming Wang, Mark Hasegawa-Johnson, Chang D. Yoo
ACL, 2023  
project page / arXiv


Listen, Decipher and Sign: toward Unsupervised Speech-to-Sign Language Recognition
Liming Wang, Junrui Ni, Heting Gao, Jialu Li, Kai Chieh Chang, Xulin Fan, Junkai Wu, Mark Hasegawa-Johnson, Chang D. Yoo
ACL (Findings), 2023  
project page / arXiv



Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
Junrui Ni*, Liming Wang*, Heting Gao*, Kaizhi Qian, Yang Zhang, Shiyu Chang, Mark Hasegawa-Johnson
Interspeech, 2022  
project page / arXiv



Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition
Liming Wang, Siyuan Feng, Mark Hasegawa-Johnson, Chang D. Yoo
ACL, 2022  
project page / arXiv

A Translation Framework for Multimodal Spoken Unit Discovery
Liming Wang, Mark Hasegawa-Johnson,
Asilomar Conference on Signals, Systems, and Computers, 2021  

Coreference by Appearance: Visually Grounded Event Coreference Resolution
Liming Wang, Shengyu Feng, Xudong Lin, Manling Li, Heng Ji, Shih-Fu Chang
The Fourth Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC), 2021.

Align or Attend? Toward more Efficient and Accurate Spoken Word discovery Using Speech-to-Image Retrieval
Liming Wang, Xinsheng Wang, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
ICASSP, 2021  
project page / arXiv

A DNN-HMM-DNN Hybrid Model for Discovering Word-like Units from Spoken Captions and Image Regions
Liming Wang, Mark Hasegawa-Johnson
Interspeech, 2020  
project page / arXiv

Multimodal Word Discovery with Spoken Descriptions and Visual Concepts
Liming Wang, Mark Hasegawa-Johnson
TASLP, 2020  
project page / arXiv

Multimodal Word Discovery with Phone Sequence and Visual Concepts
Liming Wang, Mark Hasegawa-Johnson
Interspeech, 2019  
project page / arXiv

XNMT: The eXtensible Neural Machine Translation Toolkit
Graham Neubig, Matthias Sperber, Xinyi Wang, Matthieu Felix, Austin Matthews, Sarguna Padmanabhan, Ye Qi, Devendra Sachan, Philip Arthur, Pierre Godard, John Hewitt, Rachid Riad, Liming Wang
AMTA, 2018  
project page / arXiv

Linguistic Unit Discovery from Multimodal Inputs in Unwritten Languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop.
Odette Scharenborg, Laurent Besacier, Alan Black, Mark Hasegawa-Johnson, Florian Metze, Graham Neubig, Sebastian St¨uker, Pierre Godard, Markus M¨uller, Lucas Ondel, Shruti Palaskar, Philip Arthur, Francesco Ciannella, Mingxing Du, Elin Larsen, Danny Merkx, Rachid Riad, Liming Wang, Emmanuel Dupoux
ICASSP, 2018  
project page / arXiv


Template: Jon Barron