In this project, we advance the research for theory and fundamentals of spiking neural network, with applications in always-on auditive intelligence. The key research problems include neural encoding, energy efficient auditory models, event-driven end-to-end spiking neural network system integration.

Project Duration: 11 May 2020 – 10 May 2024

Funding Source: RIE 2020 Industry Alignment Fund – Industry Collaboration Projects (IAF-ICP)

Acknowledgment: This research work is supported by Programmatic Grant No. I2001E0053 from the Singapore Government’s Research, Innovation and Enterprise 2020 plan (Advanced Manufacturing and Engineering domain).

PUBLICATIONS

Journal Article

• Xinyi Chen*, Qu Yang*, Jibin Wu, Haizhou Li, , Kay Chen Tan, "A Hybrid Neural Coding Approach for Pattern Recognition With Spiking Neural Networks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 5, pp. 3064-3078, May 2024, doi: 10.1109/TPAMI.2023.3339211
• Qu Yang*, Malu Zhang*, Jibin Wu, Kay Chen Tan, Haizhou Li, "LC-TTFS: Towards Lossless Network Conversion for Spiking Neural Networks with TTFS Coding", IEEE Transactions on Cognitive and Developmental Systems 2023, DOI: 10.1109/TCDS.2023.3334010.
• Jibin Wu, Yansong Chua, Malu Zhang, Guoqi Li, Haizhou Li, Kay Chen Tan, "A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks," in IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 1, pp. 446-460, Jan. 2023, DOI: 10.1109/TNNLS.2021.3095724.
• Siqi Cai, Peiwen Li, Enze Su, Qi Liu, and Longhan Xie, "A Neural-Inspired Architecture for EEG-Based Auditory Attention Detection," in IEEE Transactions on Human-Machine Systems, vol. 52, no. 4, pp. 668-676, Aug. 2022, DOI: 10.1109/THMS.2022.317621.
• Jibin Wu, Qi Liu, Malu Zhang, Zihan Pan, Haizhou Li, Kay Chen Tan, "HuRAI: A brain-inspired computational model for human-robot auditory interface", Neurocomputing, Volume 465, Issue C, 20 November 2021, pp 103–113, https://doi.org/10.1016/j.neucom.2021.08.115
• Zihan Pan, Malu Zhang, Jibin Wu, Jiadong Wang, Haizhou Li, "Multi-Tone Phase Coding of Interaural Time Difference for Sound Source Localization With Spiking Neural Networks," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 2656-2670, July 2021, DOI: 10.1109/TASLP.2021.3100684.
• Xinyuan Qian, Qi Liu, Jiadong Wang, and Haizhou Li, “Three-dimensional Speaker Localization: Audio-refined Visual Scaling Factor Estimation”, in IEEE Signal Processing Letters, vol. 28, pp. 1405-1409, June 2021, DOI: 10.1109/LSP.2021.3092959.
• Zhixuan Zhang and Qi Liu, “Spike-event-driven deep spiking neural network with temporal encoding”,in IEEE Signal Processing Letters, vol. 28, pp. 484-488, February 2021, DOI: 10.1109/LSP.2021.3059172.
• Qi Liu and Jibin Wu, “Parameter tuning-free missing-feature reconstruction for robust sound recognition”,in IEEE Journal of Selected Topics in Signal Processing, vol. 15, no. 1, pp. 78-89, Jan. 2021, DOI: 10.1109/JSTSP.2020.3038054.
• Jibin Wu, Chenglin Xu, Daquan Zhou, Haizhou Li, Kay Chen Tan, "Progressive tandem learning for pattern recognition with deep spiking neural networks." IEEE Transactions on Pattern Analysis and Machine Intelligence 44.11 (2021): 7824-7840, Jul 2020, https://doi.org/10.48550/arXiv.2007.01204

Conference Articles

• Qianhui Liu, Jiaqi Yan, Malu Zhang, Gang Pan, Haizhou Li, "LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimization", International Joint Conference on Artificial Intelligence (IJCAI) in Jeju, Korea, August 3 - 9, 2024.
• Yang Wang, Haiyang Mei, Qirui Bao, Ziqi Wei, Mike Zheng Shou, Haizhou Li, Bo Dong, Xin Yang, "Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition" International Joint Conference on Artificial Intelligence (IJCAI) in Jeju, Korea, August 3 - 9, 2024.
• Zeyang Song, Jibin Wu, Malu Zhang, Mike Zheng Shou, Haizhou Li, "Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks", IEEE International Conference on Acoustics, Speech and Signal Processing, 2024 (International Conference on Acoustics, Speech, & Signal Processing (ICASSP), in Seoul, Korea, 14-19 April 2024
• Qu Yang∗, Qianhui Liu*, Nan Li, Meng Ge, Zeyang Song, Haizhou Li, "sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks",  IEEE International Conference on Acoustics, Speech and Signal Processing, 2024 (International Conference on Acoustics, Speech, & Signal Processing (ICASSP), in Seoul, Korea, 14-19 April 2024
• Shimin Zhang*, Qu Yang*, Chenxiang Ma, Jibin Wu, Haizhou Li, Kay Chen Tan, "TC-LIF: A Two-Compartment Spiking Neuron Model for Long-term Sequential Modelling" in the 38th Annual AAAI Conference on Artificial Intelligence (AAAI-24), Vancouver, Canada. (Accepted) (* Equal Contribution)
• Zeyang Song, Jibin Wu, Malu Zhang, Mike Zheng Shou, Haizhou Li, "Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks", 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024), Seoul, Korea, 14~19 April 2024, https://doi.org/10.48550/arXiv.2309.09469
• Qu Yang, Qianhui Liu, Nan Li, Meng Ge, Zeyang Song, Haizhou Li, "sVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks", 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024), Seoul, Korea, 14~19 April 2024, https://doi.org/10.48550/arXiv.2403.05772
• Shuang Lian, Jiangrong Shen, Qianhui Liu, Ziming Wang, Rui Yan, Huajin Tang, "Learnable Surrogate Gradient for Direct Training Spiking Neural Networks", International Joint Conference on Artificial Intelligence (IJCAI) in Macau, August 19 - 25, 2023.
• Qu Yang, Jibin Wu, Malu Zhang, Yansong Chua, Xinchao Wang, Haizhou Li, "Training Spiking Neural Networks with Local Tandem Learning", Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS 2022), November 27, 2022 - December 3, 2022, New Orleans, Louisiana, (U.S.A)
• Peiwen Li, Enze Su, Jia Li, Siqi Cai, Longhan Xie, and Haizhou Li, "ESAA: An Eeg-Speech Auditory Attention Detection Database," 2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA), Hanoi, Vietnam, November 24-26, 2022, pp. 1-6, doi: 10.1109/O-COCOSDA202257103.2022.9997944
• Zeyang Song, Qi Liu, Qu Yang and Haizhou Li, “Knowledge distillation for In-memory keyword spotting model”, in Proc. Interspeech 2022, Songdo ConvensiA, in Incheon, Korea, September 18 to 22, 2022.
• Qu Yang, Qi Liu, Haizhou Li, “DEEP RESIDUAL SPIKING NEURAL NETWORK FOR KEYWORD SPOTTING IN LOW-RESOURCE SETTINGS”, in Proc. Interspeech 2022, Songdo ConvensiA, in Incheon, Korea, September 18 to 22, 2022.

• Qu Yang, Jibin Wu, and Haizhou Li, “Rethinking Benchmarks for Neuromorphic Learning Algorithms”, The International Joint Conference on Neural Networks (IJCNN), Virtual Event, July 2021.
• Jiadong Wang, Jibin Wu, Malu Zhang, Qi Liu, Haizhou Li, "A Hybrid Learning Framework for Deep Spiking Neural Networks with One-Spike Temporal Coding," ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, 22 May – 27 May 2022, pp. 8942-8946, DOI: 10.1109/ICASSP43922.2022.9746792