avatar

Jian Zhu

Assistant Professor
University of British Columbia
jian.zhu (at) ubc.ca


About Me

Hi there! I am currently an assistant professor at the Linguistics Department at the University of British Columbia, an associate member of UBC CS Department, part of UBC NLP Group, and an instructor for the UBC MDS-CL Program. I am primarily interested in multilingual speech processing, natural language processing, and computational social sciences.

Before joining UBC, I was a post-doctoral research fellow at Blablablab, UMSI. I had obtained my Ph.D. in Linguistics and Scientific Computing from the Department of Linguistics and the Michigan Institute for Computational Discovery & Engineering at University of Michigan-Ann Arbor. During my Ph.D. years, I was fortunately advised by Pam Beddor and David Jurgens.

Research Interests

For students

If you are a UBC undergraduate or MDS-CL student and interested in working with me, please fill in this Google Form. I will reach out to you if our research interests are closely aligned.

News

Publications

  1. A comparison of voice similarity through acoustics, human perception and deep neural network (DNN) speaker verification systems
    Suyuan Liu, Molly Babel, Jian Zhu
    Interspeech, 2024.

  2. Eagle and finch: RWKV with matrix-valued states and dynamic recurrence
    Bo Peng, Daniel Goldstein, Quentin Anthony, ..., Jian Zhu, Rui-Jie Zhu
    Conference on Language Modeling (COLM), 2024.
    PDF Page

  3. The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language
    Jian Zhu, Changbing Yang, Farhan Samir, Jahurul Islam
    Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2024.
    PDF Code Page

  4. StarCoder 2 and The Stack v2: The Next Generation
    Anton Lozhkov, Raymond Li, Loubna Ben Allal, ..., Jian Zhu, ..., Arjun Guha, Leandro von Werra, Harm de Vries
    arXiv, 2024.
    PDF Page

  5. RWKV: Reinventing RNNs for the Transformer Era
    Bo Peng, Eric Alcaide, Quentin Anthony, ..., Jian Zhu, Rui-jie Zhu
    Findings of the Association for Computational Linguistics: EMNLP, 2023.
    PDF Page

  6. StarCoder: May the source be with you!
    Raymond Li, Loubna Ben allal, Yangtian Zi, Niklas Muennighoff, ..., Jian Zhu, ..., and others
    Transactions of Machine Learning Research, 2023.
    PDF Page

  7. Dialogue-Contextualized Re-ranking for Medical History-Taking
    Jian Zhu, Ilya Valmianski, Anitha Kannan
    Machine Learning for Health Care 2023, 2023.
    PDF Code Page

  8. Multidimensional signals and analytic flexibility: Estimating degrees of freedom in human speech analyses
    Stefano Coretta, Joseph Casillas, ,..., Jian Zhu, ..., Timo Roettger
    Advances in Methods and Practices in Psychological Sciences
    PDF Page

  9. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
    Teven Le Scao, Angela Fan, Christopher Akiki, ..., Jian Zhu, ..., and others
    arXiv, 2022.
    PDF Page

  10. Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings
    Jian Zhu, Zuoyu Tian, Yadong Liu, Cong Zhang, Chia-wen Lo
    Findings of the Association for Computational Linguistics: EMNLP, 2022.
    PDF Code Page

  11. The BigScience ROOTS Corpus: A 1.6 TB Composite Multilingual Dataset
    Hugo Laurençon, Lucile Saulnier, Thomas Wang, ..., Jian Zhu, ..., and others
    NeurIPS Datasets and Benchmarks Track, 2022.
    PDF Code Page

  12. ByT5 model for massively multilingual grapheme-to-phoneme conversion
    Jian Zhu, Cong Zhang, David Jurgens
    Interspeech, 2022.
    PDF Code Page

  13. Phone-to-audio alignment without text: A Semi-supervised Approach
    Jian Zhu, Cong Zhang, David Jurgens
    IEEE International Conference on Acoustics, Speech and Signal Processing, 2022.
    PDF Code Page

  14. Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles
    Jian Zhu, David Jurgens
    Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021.
    PDF Code Page

  15. The structure of online social networks modulates the rate of lexical change
    Jian Zhu, David Jurgens
    Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021.
    PDF Code Page

  16. Synchronising Speech Segments with Musical Beats in Mandarin and English Singing
    Cong Zhang, Jian Zhu
    Interspeech, 2021.
    PDF Page

  17. Probing the phonetic and phonological knowledge of tones in Mandarin TTS models
    Jian Zhu
    Proceedings of Speech Prosody, 2020.
    PDF Code Page

  18. UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs
    Jian Zhu, Zuoyu Tian, Sandra Kubler
    Proceedings of the 13th International Workshop on Semantic Evaluation, 2019.
    PDF Page

  19. A CNN-based tool for automatic tongue contour tracking in ultrasound images
    Jian Zhu,Will Styler, Ian Calloway
    arXiv, 2019
    PDF Code Page

  20. Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural networks
    Chaojie Zhao, Peng Zhang, Jian Zhu, Chengrui Wu, Huaimin Wang, Kele Xu
    ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
    PDF Code

  21. A CNN-based tool for automatic tongue contour tracking in ultrasound images
    Bo Li, Kele Xu, Dawei Feng, Haibo Mi, Huaimin Wang, Jian Zhu
    ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
    PDF Code

  22. Effect of several acoustic cues on perceiving Mandarin retroflex affricates and fricatives in continuous speech
    Jian Zhu,Yaping Chen
    The Journal of the Acoustical Society of America, 2016.
    PDF Page


Powered by Jekyll and Minimal Light theme.