EN δΈ­ζ–‡
N

Li Nan (李ζ₯ )

Lecturer at Tianjin Normal University

πŸ“§ tju_linan@tju.edu.cn πŸ“š Google Scholar πŸ”§ GitHub

About Me

I am a Lecturer at Tianjin Normal University. I received my Ph.D. in Computer Science and Technology from Tianjin University (2020.9-2025.3), supervised by Prof. Longbiao Wang and Prof. Jianwu Dang. My research focuses on speech signal processing, including speech enhancement, speech separation, speech recognition, voice activity detection, and other related areas. I have extensive international research experience through joint training programs at Japan Advanced Institute of Science and Technology (JAIST) and National University of Singapore.

Research Interests

Speech Enhancement Speech Separation Acoustics Voice Activity Detection Speech Recognition Large Speech Models Microphone Arrays Deep Learning Auditory Perception

Education

Ph.D. in Computer Science and Technology

Tianjin University | 2020.9 - 2025.3
Research Area: Speech Enhancement | Degree: Ph.D.
Supervisors: Prof. Longbiao Wang & Prof. Jianwu Dang

Joint Ph.D. Program

National University of Singapore | 2023.11 - 2024.11
Joint Ph.D. program between Tianjin University and NUS (CSC Scholarship)
Supervisors: Prof. Haizhou Li (IEEE Fellow) & Prof. Longbiao Wang & Prof. Jianwu Dang

Master in Computer Technology

Tianjin University | 2017.9 - 2020.6
Research Area: Far-field Speech Recognition | Degree: Master of Engineering
Supervisors: Prof. Longbiao Wang & Prof. Jianwu Dang

Master in Information Sciences / UNOKI Lab

Japan Advanced Institute of Science and Technology (JAIST) | 2019.4 - 2020.4
Dual-degree program with Tianjin University | Research Area: Voice Activity Detection | Degree: Master of Science
Supervisors: Prof. Masashi Unoki & Prof. Masato Akagi

Bachelor in Electronic and Information Science and Technology

Shandong University of Technology | 2012.9 - 2016.9
Degree: Bachelor of Engineering

Publications

Journal Papers

Chinese Academy of Sciences Q1 Top

Dual-stream Noise and Speech Information Perception based Speech Enhancement

Li, Nan, Ge, M., Wang, L., & Dang, J.
Expert Systems With Applications (ESWA), 2024
CAS Q2 Β· Top Speech Journal Β· CCF-B

Robust voice activity detection using an auditory-inspired masked modulation encoder based convolutional attention network

Li Nan, Wang L, Ge M, et al.
Speech Communication, 2024, 157: 103024
CAS Q2 Β· Top Speech Journal Β· CCF-B

HC-APNet: Harmonic Compensation Auditory Perception Network for Low-complexity Speech Enhancement

Li Nan, Wang L, Ge M, et al.
Speech Communication, 2024

Conference Papers

CCF-B

Speech and noise dual-stream spectrogram refine network with speech distortion loss for robust speech recognition

Lu Haoyu, Li Nan*, Song T, et al.
ICASSP 2023
CCF-B

Robust Voice Activity Detection Using a Masked Auditory Encoder Based Convolutional Neural Network

Li, Nan, Wang, L., Unoki, M., Li, S., Wang, R., Ge, M., & Dang, J.
ICASSP 2021, pp. 6828-6832
CCF-B

Global Signal-to-noise Ratio Estimation Based on Multi-subband Processing Using Convolutional Neural Network

Li, Nan, Ge, M., Wang, L., Unoki, M., Li, S., & Dang, J.
INTERSPEECH 2022
CCF-C

A Fast Convolutional Self-attention Based Speech Dereverberation Method for Robust Speech Recognition

Li, Nan, Ge, M., Wang, L., & Dang, J.
ICONIP, pp. 295-305
CCF-C

Dual-stream Speech Dereverberation Network Using Long-term and Short-term Cues

Li, Nan, Ge, M., Wang, L., & Dang, J.
IJCNN 2022, pp. 1-5
CCF-B

Svad: A robust, low-power, and light-weight voice activity detection with spiking neural networks

Yang Q, Liu Q, Li Nan, et al.
ICASSP 2024, pp. 221-225

πŸ“š Latest Publications

My research papers are continuously updated on Google Scholar

πŸ”— View All Papers on Google Scholar

Including papers from Expert Systems With Applications, Speech Communication, ICASSP, INTERSPEECH, and more

Patents

A Low-complexity Speech Enhancement Method Based on Auditory Perception

Patent No.: CN117219102A
Inventors: Longbiao Wang, Nan Li, Jianwu Dang

Global Signal-to-noise Ratio Estimation Method Based on Auditory Filterbank and Convolutional Neural Network

Patent No.: CN112885375A
Inventors: Longbiao Wang, Nan Li, Jianwu Dang

Speech Dereverberation Method Based on Deep Features Using Generative Adversarial Networks

Patent No.: CN109887489B
Inventors: Longbiao Wang, Nan Li, Jianwu Dang

Far-field Speech Dereverberation Method Using U-Net Structure with Convolutional Neural Networks

Patent No.: CN109949821B
Inventors: Nan Li, Bo Guan

Awards & Honors

Reviewer Experience

πŸ” Peer Review Service

I regularly serve as a reviewer for top-tier journals and conferences in speech processing, signal processing, and machine learning. My reviewing work helps maintain the quality and integrity of academic research in these fields.

IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
IEEE
Neural Networks & Deep Learning
Speech Communication
Elsevier
Speech Processing & Acoustics
INTERSPEECH
ISCA
Speech Communication & Technology

Review Statistics

50+
Papers Reviewed
3
Journals/Conferences
2
Years Active

Research Projects

... Total Visits
... Unique Visitors
... Page Views

πŸ—ΊοΈ Visitor Locations

πŸ“ Real-time visitor location tracking (last 50 visitors)