Faculty Profiles - XUE Wei | The Hong Kong University of Science and Technology

2025 1

Importance Weighting Can Help Large Language Models Self-Improve

Proceeding of the 39th Annual AAAI Conference on Artificial Intelligence, v. 39, (23), April 2025
Jiang, Chunyang; Chan, Chi-Min; Xue, Wei; Liu, Qifeng; Guo, Yike
Conference paper

2024 14

AttnZero: Efficient Attention Discovery for Vision Transformers

Lecture Notes in Computer Science, v. 15063, October 2024, p. 20-37
Li, Lujun; Wei, Zimian; Dong, Peijie; Luo, Wenhan; Xue, Wei; Liu, Qifeng; Guo, Yike
Conference paper

Auto-GAS: Automated Proxy Discovery for Training-Free Generative Architecture Search

Computer Vision – ECCV 2024, October 2024, p. 38-55, Book series: Lecture Notes in Computer Science. v. 15063
Li, Lujun; Sun, Haosen; Li, Shiwen; Dong, Peijie; Luo, Wenhan; Xue, Wei; Liu, Qifeng; Guo, Yike
Conference paper

Can LLMs" Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation

Zhou, Ziya; Wu, Yuhang; Wu, Zhiyue; Zhang, Xinyue; Yuan, Ruibin; Ma, Yinghao; Wang, LU; Benetos, Emmanouil; Xue, Wei; Guo, Yike
Conference paper

CHATEVAL: Towards better LLM-based evaluators through multi-agent debate

12th International Conference on Learning Representations, ICLR 2024 / International Conference on Learning Representations, ICLR. International Conference on Learning Representations, ICLR, 2024
Chan, Chi-Min; Chen, Weize; Su, Yusheng; Yu, Jianxuan; Xue, Wei; Zhang, Shanghang; Fu, Jie; Liu, Zhiyuan
Conference paper

ChatMusician: Understanding and Generating Music Intrinsically with LLM

Yuan, Ruibin; Lin, Hanfeng; Wang, Yi; Tian, Zeyue; Wu, Shangda; Shen, Tianhao; Zhang, Ge; Wu, Yuhang; Liu, Cong; Zhou, Ziya; Ma, Ziyang; Xue, Liumeng; Wang, Ziyu; Liu, Qin; Zheng, Tianyu; Li, Yizhi; Ma, Yinghao; Liang, Yiming; Chi, Xiaowei; Liu, Ruibo; Wang, Zili; Li, Pengfei; Wu, Jingcheng; Lin, Chenghua; Liu, Qifeng; Jiang, Tao; Huang, Wenhao; Chen, Wenhu; Benetos, Emmanouil; Fu, Jie; Xia, Gus; Dannerberg, Roger; Xue, Wei; Kang, Shiyin; Guo, Yike
Conference paper

ComposerX: Multi-Agent Symbolic Music Composition with LLMs

Deng, Qixin; Yang, Qikai; Yuan, Ruibin; Huang, Yipeng; Wang, Yi; Liu, Xubo; Tian, Zeyue; Pan, Jiahao; Zhang, Ge; Lin, Hanfeng; Li, Yizhi; Ma, Yinghao; Fu, Jie; Lin, Chenghua; Benetos, Emmanouil; Wang, Wenwu; Xia, Guangyu; Xue, Wei; Guo, Yike
Conference paper

DetKDS: Knowledge Distillation Search for Object Detectors

Li, Lujun; Bao, Yufan; Dong, Peijie; Yang, Chuanguang; Li, Anggeng; Luo, Wenhan; Liu, Qifeng; Xue, Wei; Guo, Yike
Conference paper

Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models

Li, Lujun; Dong, Peijie; Tang, Zhenheng; Liu, Xiang; Wang, Qiang; Luo, Wenhan; Xue, Wei; Liu, Qifeng; Chu, Xiaowen; Guo, Yike
Conference paper

FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation

Chen, Jianyi; Xue, Wei; Tan, Xu; Ye, Zhen; Liu, Qifeng; Guo, Yike
Conference paper

FlashSpeech: Efficient Zero-Shot Speech Synthesis

Ye, Zhen; Ju, Zeqian; Liu, Haohe; Tan, Xu; Chen, Jianyi; Lu, Yiwen; Sun, Peiwen; Pan, Jiahao; Bian, Weizhen; He, Shulin; Liu, Qifeng; Guo, Yike; Xue, Wei
Conference paper

FM-OV3D: Foundation Model-Based Cross-Modal Knowledge Blending for Open-Vocabulary 3D Detection

Proceedings of the AAAI Conference on Artificial Intelligence, v. 38, (15), March 2024, p. 16723-16731
Zhang, Dongmei; Li, Chang; Zhang, Renrui; Xie, Shenghao; Xue, Wei; Xie, Xiaodong; Zhang, Shanghang
Conference paper

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation

Chan, Chi-min; Xu, Chunpu; Yuan, Ruibin; Luo, Hongyin; Xue, Wei; Guo, Yike; Fu, Jie
Conference paper

Vida: Homeostatic Visual Domain Adapter For Continual Test Time Adaptation

12th International Conference on Learning Representations, ICLR 2024 / International Conference on Learning Representations, ICLR. International Conference on Learning Representations, ICLR, 2024
Liu, Jiaming; Yang, Senqiao; Jia, Peidong; Zhang, Renrui; Lu, Ming; Guo, Yandong; Xue, Wei; Zhang, Shanghang
Conference paper

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation

Qi, Xingqun; Pan, Jiahao; Li, Peng; Yuan, Ruibin; Chi, Xiaowei; Li, Mengfei; Luo, Wenhan; Xue, Wei; Zhang, Shanghang; Liu, Qifeng; Guo, Yike
Conference paper

2023 8

Deep Cross-Modal Retrieval Between Spatial Image and Acoustic Speech

IEEE Transactions on Multimedia, v. 26, October 2023, article number 10285477, p. 4480-4489
Qian, Xinyuan; Xue, Wei; Zhang, Qiquan; Tao, Ruijie; Li, Haizhou
Article

CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model

MM '23: Proceedings of the 31st ACM International Conference on Multimedia / Association for Computing Machinery. New York, NY : Association for Computing Machinery, 2023, p. 1831-1839
Ye, Zhen; Xue, Wei; Tan, Xu; Chen, Jie; Liu, Qifeng; Guo, Yike
Conference paper

GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, v. 2023-June, May 2023, article number 10095551
Li, Guanjun; Xue, Wei; Liu, Wenju; Yi, Jiangyan; Tao, Jianhua
Conference paper

Generated Therapeutic Music Based on the ISO Principle

Communications in Computer and Information Science, v. 2007, February 2024, p. 32-45
Qiu, Zipeng; Yuan, Ruibin; Xue, Wei; Jin, Yucheng
Conference paper

LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT

Proceedings of the International Society for Music Information Retrieval Conference, v. 2023, November 2023, p. 343-351
Zhuo, Le; Yuan, Ruibin; Pan, Jiahao; Ma, Yinghao; Li, Yizhi; Zhang, Ge; Liu, Si; Dannenberg, Roger; Fu, Jie; Lin, Chenghua; Benetos, Emmanouil; Chen, Wenhu; Xue, Wei; Guo, Yike
Conference paper

Marble: Music audio representation benchmark for universal evaluation

Advances in Neural Information Processing Systems, v. 36, December 2023
Yuan, Ruibin; Tian, Zeyue; Xue, Wei; Guo, Yike
Conference paper

MoMusic: A Motion-Driven Human-AI Collaborative Music Composition and Performing System

Bian, Weizhen; Song, Yijin; Gu, Nianzhen; Chan, Tin Yan; Lo, Tsz To; Li, Tsun Sun; Wong, King Chak; Xue, Wei; Trillo, Roberto Alonso
Conference paper

NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis Based on Frequency Modulation

IJCAI International Joint Conference on Artificial Intelligence, v. 2023-August, August 2023, p. 5869-5877
Ye, Zhen; Xue, Wei; Tan, Xu; Liu, Qifeng; Guo, Yike
Conference paper

2022 2

Deep Audio-Visual Beamforming for Speaker Localization

IEEE Signal Processing Letters, v. 29, April 2022, article number 9750883, p. 1132-1136
Qian, Xinyuan; Zhang, Qiquan; Guan, Guohui; Xue, Wei
Article

Speech recognition with a hearing-aid processing scheme combining beamforming with mask-informed speech enhancement

Trends in Hearing, v. 26, January 2022
Green, Tim; Hilkhuysen, Gaston; Huckvale, Mark; Rosen, Stuart; Brookes, Mike; Moore, Alastair; Naylor, Patrick; Lightburn, Leo; Xue, Wei
Article

2021 2

Causal System Identification based Compensation for Reverberation-Robust DOA Estimation

European Signal Processing Conference, v. 2021-August, December 2021, article number 9616217, p. 1885-1889
He, Li; Xue, Wei
Conference paper

Neural Kalman filtering for speech enhancement

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, v. 2021-June, May 2021, article number 9413499, p. 7108-7112
Xue, Wei; Quan, Gang; Zhang, Chao; Ding, Guohong; He, Xiaodong; Zhou, Bowen
Conference paper

2020 4

Speech Enhancement Based on Modulation-Domain Parametric Multichannel Kalman Filtering

IEEE/ACM Transactions on Audio Speech and Language Processing, v. 29, November 2020, article number 9272832, p. 393-405
Xue, Wei; Moore, Alastair H.; Brookes, Mike; Naylor, Patrick A.
Article

SkipConvNet: Skip convolutional neural network for speech dereverberation using optimally smoothed spectral mapping

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v. 2020-October, October 2020, p. 3935-3939
Kothapally, Vinay; Xia, Wei; Ghorbani, Shahram; Hansen, John H.L.; Xue, Wei; Huang, Jing
Conference paper

Sound event localization and detection based on multiple DOA beamforming and multi-task learning

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v. 2020-October, October 2020, p. 5091-5095
Xue, Wei; Tong, Ying; Zhang, Chao; Ding, Guohong; He, Xiaodong; Zhou, Bowen
Conference paper

The JD AI speaker verification system for the FFSVC 2020 challenge

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v. 2020-October, October 2020, p. 3476-3480
Tong, Ying; Xue, Wei; Huang, Shanluo; Fan, Lu; Zhang, Chao; Ding, Guohong; He, Xiaodong
Conference paper

2019 3

Noise covariance matrix estimation for rotating microphone arrays

IEEE/ACM Transactions on Audio, Speech and Language Processing, v. 27, (3), March 2019, article number 8540424, p. 519-530
Moore, Alastair H.; Xue, Wei; Naylor, Patrick A.; Brookes, Mike
Article

Direct-path signal cross-correlation estimation for sound source localization in reverberation

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v. 2019-September, September 2019, p. 2693-2697
Xue, Wei; Tong, Ying; Ding, Guohong; Zhang, Chao; Ma, Tao; He, Xiaodong; Zhou, Bowen
Conference paper

Estimation of the Noise Covariance Matrix for Rotating Sensor Arrays

Conference Record - Asilomar Conference on Signals, Systems and Computers, v. 2018-October, February 2019, article number 8645397, p. 1936-1941
Moore, Alastair H.; Xue, Wei; Naylor, Patrick A.; Brookes, Mike
Conference paper

2018 4

Modulation-Domain Multichannel Kalman Filtering for Speech Enhancement

IEEE/ACM Transactions on Audio, Speech, and Language Processing, v. 26, (10), October 2018, article number 8375666, p. 1833-1847
Xue, Wei; Moore, Alastair H.; Brookes, Mike; Naylor, Patrick A.
Article

Binaural mask-informed speech enhancement for hearing AIDS with head tracking

16th International Workshop on Acoustic Signal Enhancement, IWAENC 2018 - Proceedings / IEEE. Piscataway, NJ : IEEE, 2018, p. 461-465, article number 8521361
Moore, Alastair H.; Lightburn, Leo; Xue, Wei; Naylor, Patrick A.; Brookes, Mike
Conference paper

Modulation-domain parametric multichannel Kalman filtering for speech enhancement

European Signal Processing Conference, v. 2018-September, December 2018, article number 8552954, p. 2509-2513
Xue, Wei; Moore, Alastair H.; Brookes, Mike; Naylor, Patrick A.
Conference paper

Multichannel Kalman Filtering for Speech Ehnancement

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, v. 2018-April, September 2018, article number 8461903, p. 41-45
Xue, Wei; Moore, Alastair H.; Brookes, Mike; Naylor, Patrick A.
Conference paper

2017 2

Frequency-domain under-modelled blind system identification based on cross power spectrum and sparsity regularization

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings / IEEE. Piscataway, NJ : IEEE, 2017, p. 591-595, article number 7952224
Xue, Wei; Brookes, Mike; Naylor, Patrick A.
Conference paper

Multilingual I-vector based statistical modeling for music genre classification

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v. 2017-August, August 2017, p. 459-463
Dai, Jia; Xue, Wei; Liu, Wenju
Conference paper

2016 5

A novel codebook representation method and encoding strategy for bag-of-words based acoustic event classification

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 / IEEE. Piscataway, NJ : IEEE, 2016, p. 31-34, article number 7415326
Dai, Jia; Ni, Chongjia; Xue, Wei; Liu, Wenju
Conference paper

Cross-correlation based under-modelled multichannel blind acoustic system identification with sparsity regularization

European Signal Processing Conference, v. 2016-November, December 2016, article number 7760342, p. 718-722
Xue, Wei; Brookes, Mike; Naylor, Patrick A.
Conference paper

Long short-term memory recurrent neural network based segment features for music genre classification

Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016 / IEEE. Piscataway, NJ : IEEE, 2016, article number 7918369
Dai, Jia; Liang, Shan; Xue, Wei; Ni, Chongjia; Liu, Wenju
Conference paper

Semi-supervised learning of bottleneck feature for music genre classification

Communications in Computer and Information Science, v. 663, October 2016, p. 552-562
Dai, Jia; Liu, Wenju; Zheng, Hao; Xue, Wei; Ni, Chongjia
Conference paper

Under-modelled blind system identification for time delay estimation in reverberant environments

2016 International Workshop on Acoustic Signal Enhancement, IWAENC 2016 / IEEE. Piscataway, NJ : IEEE, 2016, article number 7602923
Xue, Wei; Brookes, Mike; Naylor, Patrick A.
Conference paper

2015 3

Noise Robust Direction of Arrival Estimation for Speech Source with Weighted Bispectrum Spatial Correlation Matrix

IEEE Journal on Selected Topics in Signal Processing, v. 9, (5), August 2015, article number 7067389, p. 837-851
Xue, Wei; Liu, Wenju; Liang, Shan
Article

Joint optimization of recurrent networks exploiting source auto-regression for source separation

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v. 2015-January, September 2015, p. 3307-3311
Nie, Shuai; Xue, Wei; Liang, Shan; Zhang, Xueliang; Liu, Wenju; Qiao, Liwei; Li, Jianping
Conference paper

Two-stage multi-target joint learning for monaural speech separation

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, v. 2015-January, September 2015, p. 1503-1507
Nie, Shuai; Liang, Shan; Xue, Wei; Zhang, Xueliang; Liu, Wenju; Dong, Like; Yang, Hong
Conference paper

2014 3

The analysis of the simplification from the ideal ratio to binary mask in signal-to-noise ratio sense

Speech Communication, v. 59, April 2014, p. 22-30
Liang, Shan; Liu, Wenju; Jiang, Wei; Xue, Wei
Article

DOA estimation of speech source in noisy environments with weighted spatial bispectrum correlation matrix

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings / IEEE. Piscataway, NJ : IEEE, 2014, p. 2282-2286, article number 6854006
Xue, Wei; Liang, Shan; Liu, Wenju
Conference paper

Weighted spatial bispectrum correlation matrix for DOA estimation in the presence of interferences

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech and Communication Association, 2014, p. 2228-2232
Xue, Wei; Liang, Shan; Liu, Wenju
Conference paper

2013 2

The optimal ratio time-frequency mask for speech separation in terms of the signal-to-noise ratio

Journal of the Acoustical Society of America, v. 134, (5), November 2013, p. EL452-EL458
Liang, Shan; Liu, Wenju; Jiang, Wei; Xue, Wei
Article

Interference robust DOA estimation of human speech by exploiting historical information and temporal correlation

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech and Communication Association, 2013, p. 2895-2899
Xue, Wei; Liang, Shan; Liu, Wenju
Conference paper

2012 1

Direction of arrival estimation based on subband weighting for noisy conditions

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, v. 1, September 2012, p. 142-145
Xue, Wei; Liu, Wenju
Conference paper

EMIA4110	Practical Machine Learning
EMIA6500N	Digital Audio Processing
IIMP6090	Postgraduate Seminar

EMIA4110	Practical Machine Learning
IIMP6090	Postgraduate Seminar

EMIA4110	Practical Machine Learning
IIMP6090	Postgraduate Seminar

Research Interest

Publications

2025 1

2024 14

2023 8

2022 2

2021 2

2020 4

2019 3

2018 4

2017 2

2016 5

2015 3

2014 3

2013 2

2012 1

Conference paper 1

Conference paper 14

Article 1

Conference paper 7

Article 2

Conference paper 2

Article 1

Conference paper 3

Article 1

Conference paper 2

Article 1

Conference paper 3

Conference paper 2

Conference paper 5

Article 1

Conference paper 2

Article 1

Conference paper 2

Article 1

Conference paper 1

Conference paper 1

2019 3

2018 4

2017 2

2016 5

2015 3

2014 3

2013 2

2012 1

Teaching Assignment

Research Postgraduate (RPG) Supervision

From January 2022 to December 2025 (As of 25 April 2025)

Current RPGs

Projects

From January 2023 to December 2025

Your browser is out of date!