Xi'an Jiaotong-Liverpool University

首页 > 智能科学系 > Shengchen Li

Profile

Graduated from world-famous Centre for Digital Music (C4DM), Queen Mary University of London (QMUL), Shengchen Li has focused on machine listening techniques on various types of signals including music, acoustic signal and biomedical signal. Being a pianist in young age, Shengchen has a special interest in computer music research including but not limited to automatic music generation, computational musicology and objective evaluation of piano performance.

His fellow students have named among the winner / top-ranked teams of IEEE AASP Data Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE), which is a competitive and top-ranked data challenge in acoustic signal processing society, in the year of 2018-2021.

Shengchen is currently the leader of research group of machine learning and data analytics. He also has a fee studentship available for application at this stage. You are also more than welcome to visit Shengchen's personal webpage at https://shengchenli.github.io/ for details.

Qualifications
- PhD, Queen Mary University of London, awarded by 31st March 2016
- BSc (First Class), Queen Mary University of London, awarded by 31st July 2011
Experience
- Assistant Professor, Xi'an Jiaotong - Liverpool University, Mar 2021 -
- Lecturer, Beijing Unviersity of Posts and Telecommunications, Sep 2016 - Mar 2021
Research interests
- Efficient Machine Learning (Model Compression)
- Machine Learning
- Machine Listening
Articles
- Yuqiang Li, Shengchen Li and Györge Fazekas. How Music Features and Musical Data Representations Affect Objective Evaluation of Music Composition: A Review of the CSMT Data Challenge 2020, In Proceeding of 23rd International Society of Music Information Retrieval Conference, pages 93-99, 2022.
- Shengchen Li and Ke Tian. Unsupervised Phonocardiogram Analysis With Distribution Density Based Variational Auto-Encoders, Frontiers in Medicine, Vol. 8, pp. 1071, 2021.
- Shengchen Li, Ke Tian and Rui Wang. Unsupervised Heart Abnormality Detection Based on Phonocardiogram Analysis with Beta Variational Auto-Encoders, In Proceeding of IEEE International Conference on Acoustic, Audio and Signal Processing (ICASSP), pages 8353–8357, 2021.
- Shengchen Li, Yinji Jing and Györge Fazekas. A novel dataset for the identification of computer-generated melodies in the csmt challenge. In Proceedings of 8th Conference on Sound and Music Technology, pages 177-186, 2021.
- Chunxia Ren and Shengchen Li. Adversarial domain adaptation for open set acoustic scene classification. In Proceeding of 8th Conference on Sound and Music Technology, pages 93-104, 2021.
- Chunxia Ren and Shengchen Li. Two-stage classification learning for open set acoustic scene classification. In Proceeding of 8th Conference on Sound and Music Technology, pages 124-133, 2021.
- Yuanbo Hou, Frank Soong, Jian Luan, and Shengchen Li. Transfer learning for improving singing-voice detection in polyphonic instrumental music. In Proceedings of Conference of the International Speech Communication Association (INTERSPEECH), 2020.
- Yusong Wu, Shengchen Li, Chengzhu Yu, Heng Lu, Chao Weng, Liqiang Zhang, and Dong Yu. Peking opera synthesis via duration informed attention network. In Proceedings of Conference of the International Speech Communication Association (INTERSPEECH), 2020.
- Shengchen Li and Yusong Wu. An introduction to a symbolic music dataset of chinese guqin pieces and its application example (in Chinese). Journal of Fudan University, 59(3):276–285, 2020.
- Kun Chen, Yusong Wu, Ziyue Wang, Xuan Zhang, Fudong Nian, Shengchen Li, and Xi Shao. Audio captioning based on transformer and pre-trained CNN. In Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop, pages 21–25, 2020.
- Ziming Li and Shengchen Li. A comparison of melody created by artificial intelligence and human based on mathematical model. In Proceedings of the 7th Conference on Sound and Music Technology (CSMT), volume 635 of Lecture Notes on Electronic Engineering, pages 121–130, 2019.
- Yusong Wu and Shengchen Li. Distinguishing chinese Guqin and western baroque pieces based on statistical model analysis of melodies. In Proceeding of the 14th International Symposium on Computer Music Multidisciplinary Research (CMMR), page 931–942, 2019.
- Zhitong Li, Yuanbo Hou, Xiang Xie, Shengchen Li, Liqiang Zhang, Shixuan Du, and Wei Liu. Multi-level attention model with deep scattering spectrum for acoustic scene classification. In IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pages 396–401, 2019.
- Jun Wang, Shengchen Li, and Wenwu Wang. SVD-based channel pruning for convolutional neural network in acoustic scene classification model. In IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pages 390–395, 2019.
- Yuanbo Hou, Qiuqiang Kong, Shengchen Li, and Mark D. Plumbley. Sound event detection with sequentially labelled data based on connectionist temporal classification and unsupervised clustering. In Proceeding of IEEE International Conference on Acoustic, Audio and Signal Processing (ICASSP), pages 46–50, 2019.
- Lei Guan, Yinji Jing, Shengchen Li, and Ru Zhang. A standard MIDI file steganography based on music perception. In Proceeding of the 6th Conference on Sound and Music Technology (CSMT), volume 568 of Lecture Notes on Electronic Engineering, pages 99–107. Springer, 2018.
- Jia’nan Song and Shengchen Li. Bird sound detection based on binarized convolutional neural networks. In Proceedings of the 6th Conference on Sound and Music Technology (CSMT), volume 568 of Lecture Notes on Electronic Engineering, pages 63–71. Springer, 2018.
- Yuanbo Hou, Qiuqiang Kong, and Shengchen Li. A comparison of attention mechanisms of convolutional neural network in weakly labelled audio tagging. In Proceedings of the 6th Conference on Sound and Music Technology (CSMT), volume 568 of Lecture Notes on Electronic Engineering, pages 85–96. Springer, 2018.
- Yuanbo Hou, Qiuqiang Kong, Jun Wang, and Shengchen Li. Polyphonic audio tagging with sequentially labelled data using crnn with learnable gated linear units. In Proceeding of Detection and Classification of Acoustic Scenes and Events Workshop, pages 78–82, 2018.
- Songjiang Zhou, Shengchen Li, and Ming Liu. A low power and high-speed decoder design based on FPGA (in Chinese). Application of Electronic Techniques, 44(4):27–32, 2018.
- Bo Yang, Shengchen Li, and Baoqiang Han. Research of energy distributions of violin harmonics based on mathematical models (in Chinese). Journal of Fudan University, 57(3):314–319, 2018.
- Yuanbo Hou, Qiuqiang Kong, and Shengchen Li. Audio tagging with connectionist temporal classification model using sequential labelled data. In Proceedings of the 2018 International Conference on Communications, Signal Processing and Systems (CSPS) Volume II: Signal Processing, pages 955–964, 2018.
- Shengchen Li, Simon Dixon, and Mark D. Plumbley. A demonstration of hierarchical structure usage in expressive timing analysis by model selection tests. In Proceeding of Chinese Control Conference, pages 3190–3195, 2018.
- Jun Wang and Shengchen Li. Comparing the influence of depth and width of deep neural network based on fixed number of parameters for audio event detection. In Proceeding of IEEE International Conference on Acoustic, Audio and Signal Processing (ICASSP), pages 2681–2685, 2018.
- Shengchen Li, Simon Dixon, and Mark D. Plumbley. Clustering expressive timing with regressed polynomial coef- ficients demonstrated by a model selection test. In Proceeding of 18th International Society of Music Information Retrieval Conference, pages 457–463, 2017.
- Shengchen Li, Simon Dixon, Dawn A. A. Black, and Mark D. Plumbley. A model selection test for factors affecting the choice of expressive timing clusters for a phrase. In Proceeding of 13th Sound and Music Computing, pages 247–252, 2016.
- Shengchen Li, Dawn A. A. Black, and Mark D. Plumbley. The clustering of expressive timing within a phrase in classical piano performances by gaussian mixture models. In 11th International Symposium on Computer Music Multidisciplinary Research (CMMR) Revised Selected Papers, volume 9617 of Lecture Notes in Computer Science, pages 322–345. Springer, 2015.
- Shengchen Li, Dawn A. A. Black, Elaine Chew, and Mark D. Plumbley. Evidence that phrase-level tempo variation may be represented using a limited dictionary. In Proceeding of International Conference on Music Perception and Cognition (ICMPC) 2014, pages 413–419, 2014.
Proceedings
- Haifeng Li, Shengchen Li, Lin Ma, Chunying Fang, Yidan Zhu, Proceeding of 7th Conference on Sound and Music Technology, Selected Revised Paper, Lecture Notes on Electronic Engineering, Springer
- Wei Li, Shengchen Li, Xi Shao, Zijin Li, Proceeding of 6th Conference on Sound and Music Technology, Selected Revised Paper, Lecture Notes on Electronic Engineering, Springer
Books, monographs, compilations and manuals
- Ke Tian, Guoheng Fu, Shengchen Li, Gang Tang, and Xi Shao. Anomaly machine detection algorithm based on semi variational auto-encoder of Mel spectrogram. Technical report, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2020.
- Yusong Wu, Kun Chen, Ziyue Wang, Xuan Zhang, Fudong Nian, Shengchen Li, and Xi Shao. Audio captioning based on transformer and pre-training for 2020 DCASE audio captioning challenge. Technical report, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2020.
- Houwei Zhu, Chunxia Ren, Jun Wang, Shengchen Li, Lizhong Wang, and Lei Yang. DCASE 2019 challenge task1 technical report. Technical report, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2019.
- Yusong Wu, Shengchen Li, Chengzhu Yu, Heng Lu, Chao Weng, and Dong Yu. Highly Expressive Peking Opera Synthesis with Durian System, Late Breaking Demo, 20th International Society of Music Information Retrieval Conference, 2019.
- Yinji Jing, Shengchen Li, An Automatic Music Generation Method Based on Given Patterns of Rhythm, Late Breaking Demo, 20th International Society of Music Information Retrieval Conference, 2019.
- Jun Wang and Shengchen Li. Detection and classification of acoustic scenes and events 2018 self-attention mechanism based system for DCASE 2018 challenge task1 and task4. Technical report, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2018, 2018.
- Jun Wang and Shengchen Li. Multi-frame concatenation for detection of rare sound events based on deep neural network. Technical report, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2017, 2017.
- Shengchen Li, Dawn A. A. Black, Elaine Chew, Tempo variegation analysis and visualization: hierarchical clustering for repetition in expressive music performance, Digital Music Research Network, 2012.
Conference presentations
- Can computers be the fair judge of music? Tutorial, Conference on Sound and Music Technology, 2019.
- Computational Methods of Expressiveness Analysis in Performed Music, Centre for Digital Music, Queen Mary University of London, on 30th Oct 2019.
- Towards hardware solutions of acoustic signal processing — Key techniques and possible future directions, University of Surrey, on 22nd May 2019.
- An Introduction of Computational Musicology, Seminar series of China Conference on Sound and Music Technology, China Northern University, 2019.
- Arts or Engineering: Music Perception and Recognition, Seminar series of China Conference on Sound and Music Technology, Fudan University, 2018,
Grants
- A research on domestic robustness for acoustic signal processing system, Gusu Innovation and Entrepreneurship Leading Talents Programme - Youth Innovation Leading Talent, Funding RMB 500,000, 2022-2025
- Acoustic Scenes Identification based on Domain Adaptation Methods, Junior Research Project, National Natural Science Foundation of China, Principal Investigator, In process, Funding RMB 240,000, Jan 2021-Dec 2023.
- Junior Promotion Fellowship, Beijing Acoustic Association, Beijing Association of Science and Technologies, Funding RMB 20,000, 2020-2022.
- The Legal Risk Analysis in the Application of Computer Assistant Composition Techniques, Strategic Collaboration, Zhongwen Law Firm, Principal Investigator, In Process, Rolling Funding RMB 50,000 per Year, since 2019.
Professional service activities
- Leader of Research Group, Machine Learning and Data Analytics, 2022
- Member of Technical Committee, Speech Dialogue and Auditory Processing, China Computer Federation, 2020.
- Steering committee member of Conference on Music and Sound Technology (CSMT) since 2018
- General Secretary of Chinese Project, Imola International Piano Festival, 2012-2013.
Courses taught
- INT307, Multimedia Security System, Sem 1, Academic Year 21/22, 22/23
- INT104, Artificial Intelligence, Sem 2, Academic Year 20/21, 21/22, 22/23
Professional memberships
- Member of CCF
- Member of IEEE
Awards and honours
- 2nd Place overall on Low-Complexity Acoustic Scenes Classification, DCASE Data Challenge, 2023
- Best Student Paper, Adversarial Domain Adaptation for Open Set Acoustic Scene Classification, Conference on Sound and Music Technology, 2020
- Reproducibility Award, automated audio captioning, IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE), 2020.
- 2nd Place overall (1st as an academic team) on automated audio captioning, IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE), 2020.
- 1st Place on Open-set Acoustic Scenes Identification, IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE), 2019
- Best Student Paper, A Standard MIDI File Steganography Based on Music Perception, Conference on Sound and Music Technology, 2018

电话
+86 (0)51288973077
电子邮件
Shengchen.Li@xjtlu.edu.cn
地址
SD533(SIP Campus-Science Building)
Suzhou Dushu Lake Science and Education Innovation District
Suzhou Industrial Park
Suzhou
P.R.China
215123

Shengchen LiPhD

Profile

Qualifications

Experience

Research interests

Articles

Proceedings

Books, monographs, compilations and manuals

Conference presentations

Grants

Professional service activities

Courses taught

Professional memberships

Awards and honours