---

Introduction

Graduated from Centre for Digital Music (C4DM), Queen Mary University of London, Dr. Shengchen Li has focused on research of auditory intelligence for about more than ten years. His expertise ranges from computational musicology to acoustic signal processing with some attempts on hardware implementation of deep learning algorithms. Shengchen currently hosts a NSFC (Natural Science Foundation of China) project named Acoustic Scenes Identification based on Domain Adaptation. Shengchen is also a member of task force on Speech Dialogue and Auditory Processing, China Computer Federation.

Serving as an assistant professor in Xi'an Jiaotong-Liverpool University, Shengchen is currently the module leader of INT306 (Computer Auditory Systems) and INT104 (Artificial Intelligence). Shengchen is a good student team leader. His research team has won high ranks at the DCASE (Detection and Classification of Acoustic Scenes and Events) data challenge. Shengchen is recruiting new PhD students / RAs who are interested in auditory intelligence research throughout the academic year. From case to case, there might be scholarship available for PhD applicants.

For SURF application please refer to RA / PhD Recruitment.

You may want to visit my official page as well.

---

News

10 Jan 2024: A paper named " Acoustic Scene Classification across Cities and Devices via Feature Disentanglement " has been accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP).

03 Dec 2023: Yizhou Tan has enrolled in XJTLU as my PhD student.

14 Dec 2023: A paper named "TF-SepNet: An Efficient 1D Kernel Design in Cnns for Low-Complexity Acoustic Scene Classification"

has been accpeted by IEEE ICASSP.

13 Nov 2023: My student Yuqiang Li has presented his paper "Pitch Class and Octave-based Pitch Embedding Training Strategies of Symbolic Music Generation. Proceeding of 16th International Symposium on Computer Music Multidisciplinary Research" on CMMR 2023.

01 Sep 2023: Yiqiang Cai has enrolled in XJTLU as my PhD student.

07 Jun 2023: I have given a webminar of music AI at Tsinghua University.

31 May 2023: The team leading by me has been nominated as the runner-up of DCASE Challenge 2023 Task 1

18 May 2023: A paper named "Transductive Feature Space Regularization for Few-shot Bioacoustic Event Detection" has been accepted by INTERSPEECH 2023.

04 May 2023: A paper named "Measuring channel sparsity for neural network pruning in acoustic scene classification" has been accepted by the 10th Conference on Sound and Music Computing (CSMT)

01 Mar 2023: Yuxuan Liu has enrolled in XJTLU as my PhD student.

For more news please refer to this page.

---

Selected Publications All Publications »

• ICASSP 2024"TF-SepNet: An Efficient 1D Kernel Design in Cnns for Low-Complexity Acoustic Scene Classification", Yiqinag Cai, Peihong Zhang, Shengchen Li, 48th IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP'24), 2024.
• TASLP 2024"Acoustic Scene Classification Across Cities and Devices via Feature Disentanglement", Yizhou Tan, Haojun Ai, Shengchen Li, Mark D. Plumbley, IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), pages 1286-1297, 2024.
• INTERSPEECH 2023"Transductive Feature Space Regularization for Few-shot Bioacoustic Event Detection", Yizhou Tan, Haojun Ai, Shengchen Li, Fang Zhang, Proceedings of the Twenty-Fourth Conference of the International Speech Communication Association (INTERSPEECH), pages 571-575, 2023.
• ISMIR 2022"How Music Features and Musical Data Representations Affect Objective Evaluation of Music Composition: a Review of the CSMT data challenge 2020", Yuqiang Li, Shengchen Li, George Fazekas, Proceedings of Annual Conference of International Society of Music Information Retrieval, pp. 93--99, 2022.
• FMed 2021"Unsupervised Phonocardiogram Analysis With Distribution Density Based Variational Auto-Encoders", Shengchen Li, Ke Tian, Frontiers in Medicine, Vol. 8, pp. 1071, 2021.
• ICASSP 2021“Unsupervised Heart Abnormality Detection Based on Phonocardiogram Analysis with Beta Variational Auto-Encoders”, Shengchen Li, Ke Tian, Rui Wang, Proceedings of the 45th IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP'21) , IEEE Signal Processing Society, Toronto, Canada, 6-11 June 2021.
• INTERSPEECH 2020"Transfer Learning for Improving Singing-Voice Detection in Polyphonic Instrumental Music", Yuanbo Hou, Frank K. Soong, Jian Luan, Shengchen Li, Proceedings of INTERSPEECH 2020, Shanghai, China, 26-29 Oct 2020.
• INTERSPEECH 2020"Peking Opera Synthesis via Duration Informed Attention Network", Yusong Wu, Shengchen Li, Chengzhu Yu, Heng Lu, Chao Weng, Liqiang Zhang, Dong Yu, Proceedings of INTERSPEECH 2020, Shanghai, China, 26-29 Oct 2020.
• ICASSP 2019 "Sound Event Detection with Sequentially Labelled Data based on Connectionist Temporal Classification and Unsupervised Clustering", Yuanbo Hou, Qiuqiang Kong, Shengchen Li, Mark D. Plumbley, Proceedings of the 44th IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP'19), IEEE Signal Processing Society, Brighton, United Kingdom, 12-17 May 2019.
• ICASSP 2018 "Comparing the Influence of Depth and Width of Deep Neural Network Based on Fixed Number of Parameters for Audio Event Detection", Jun Wang, Shengchen Li, Proceedings of the 43rd IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP'18), IEEE Signal Processing Society, Calgary, Canada, 15-20 April 2018.

All Publications »

---

Awards and Honors

• DCASE 2023 Yiqiang CAI, Minyu LIN and Shengchen LI were named among the runner-up of DCASE Challenge 2023 Task 1 with collegues from Nanjing University of Posts and Telecommunications.
• Suzhou Shengchen LI, Junior Academia Innovative Fellowship, Gusu Leadership Fellowship, Suzhou Government, July 2022 - July 2025
• DCASE 2020 Yusong WU, Kun CHEN and Shengchen LI were named among the runner-up of DCASE Challenge 2020 Task 6 with collegues from Nanjing University of Posts and Telecommunications.
• BAST Shengchen LI, Junior Promotion Fellowship, Beijing Acoustic Association, Beijing Association of Science and Technologies, 2020-2022
• DCASE 2019 Chunxia REN, Jun WANG and Shengchen LI were named among a winner of DCASE Challenge 2019 Task 1C with collegues from Samsung Research Centre, Beijing.
• CSMT 2018 Shengchen LI, Scholar Contribution Award, 6th Conference on Sound and Music Technology
• CSC 2011 Shengchen LI, No. 2011647018, Public Funding of Oversea Studying for High-level University Establishment, China Scholarship Council