Liming Wang

Electrical and Computer Engineering
University of Illinois, Urbana-Champaign
Email: lwang114@illinois.edu
Github

Welcome!

• Unsupervised representation learning for multimodal dialogue systems
• Multimodal coreference resolution
• Mathematical model of spoken language acquisition

Publications

Journal Paper

• Liming Wang, Mark Hasegawa-Johnson. Multimodal Word Discovery with Spoken Descriptions and Visual Concepts. Transactions on Audio, Speech and Language Processing, 2020. paper

Conference Paper

• Junrui Ni, Liming Wang, Heting Gao, Kaizhi Qian, Yang Zhang, Shiyu Chang and Mark Hasegawa-Johnson. Unsupervised text-to-speech synthesis by unsupervised automatic speech recognition. Accepted by Interspeech, 2022. paper code demo
• Liming Wang, Siyuan Feng, Mark Hasegawa-Johnson and Chang D. Yoo. Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition. Annual Meeting of the Association for Computational Linguistics, 2022. paper code
• Liming Wang, Mark Hasegawa-Johnson. A Translation Framework for Multimodal Spoken Unit Discovery. Asilomar Conference on Signals, Systems, and Computers, 2021. slides
• Liming Wang, Shengyu Feng, Xudong Lin, Manling Li, Heng Ji and Shih-Fu Chang. Coreference by Appearance: Visually Grounded Event Coreference Resolution. The Fourth Workshop on Computational Models of Reference, Anaphora andCoreference (CRAC), 2021. paper
• Liming Wang, Mark Hasegawa-Johnson. Align or Attend? Toward More Efficient and Accurate Spoken Word Discovery Using Speech-To-Image Retrieval. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021. paper
• Liming Wang, Mark Hasegawa-Johnson. A DNN-HMM-DNN Hybrid Model for Discovering Word-like Units from Spoken Captions and Image Regions. Interspeech 2020. paper
• Liming Wang, Mark Hasegawa-Johnson. Multimodal Word Discovery with Phone Sequence and Image Concepts. Interspeech 2019 (oral presentation). paper presentation
• Graham Neubig et al., XNMT: The eXtensible Neural Machine Translation Toolkit. Proceedings of the 13th Conference of the Association for Machine Translation in the America, 2018.
• Odette Scharenborg et al., Linguistic Unit Discovery from Multimodal Inputs in Unwritten Languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop. International Conference on Acoustics, Speech and Signal Processing, 2017.

Projects and Codes

• Multimodal word discovery: code
• Math word problem solver: code and report
• Interior point method applied to SVM: Download_code dataset
• Graphical Lasso: code
• Regulatory network inference: code
• Visualization of spoken units with diffusion map:

Hobbies

• Play tennis (member of the tennis club), jogging and juggling
• Play Hulusi, a traditional Chinese flute
• My favourite podcasts: Science Friday Talking Machines