Abstract
Biological systems possess remarkable sound source localization (SSL) capabilities that are critical for survival in complex environments. This ability arises from the collaboration between the auditory periphery, which encodes sound as precisely timed spikes, and the auditory cortex, which performs spike-based computations. Inspired by these biological mechanisms, we propose a novel neuromorphic SSL model that integrates spike-based neural encoding and computation. The model employs Resonate-and-Fire (RF) neurons with a phase-locking coding (RF-PLC) method to achieve energy-efficient audio processing. The RF-PLC method leverages the resonance properties of RF neurons to efficiently convert audio signals to time-frequency representation and encode interaural time difference (ITD) cues into discriminative spike patterns. In addition, biological adaptations like frequency band selectivity and short-term memory enhance SSL capability in noisy environments. Inspired by these adaptations, we introduce a spike-driven multi-auditory attention (MAA) module that significantly improves both the accuracy and robustness of the proposed SSL model in real-world conditions. Extensive experimentation demonstrates that our model achieves state-of-the-art accuracy outperforming existing approaches. Furthermore, our model shows exceptional noise robustness and maintains high accuracy even at very low signal-to-noise ratios. By mimicking biological hearing, this neuromorphic approach contributes to the development of high-performance and explainable artificial intelligence systems capable of superior performance in real-world environments.
Original language | English |
---|---|
Title of host publication | Advances in Neural Information Processing Systems 37 (NeurIPS 2024) |
Place of Publication | San Diego, US |
Publisher | Neural information processing systems foundation |
Pages | 1-24 |
Number of pages | 24 |
Publication status | Accepted/In press - 25 Sept 2024 |
Event | The Thirty-Eighth Annual Conference on Neural Information Processing Systems - Vancouver Convention Center, Vancouver, Canada Duration: 10 Dec 2024 → 15 Dec 2024 Conference number: 38 https://neurips.cc/Conferences/2024 |
Conference
Conference | The Thirty-Eighth Annual Conference on Neural Information Processing Systems |
---|---|
Abbreviated title | NeurIPS 2024 |
Country/Territory | Canada |
City | Vancouver |
Period | 10/12/24 → 15/12/24 |
Internet address |
Keywords
- Spiking Neural Networks
- Resonate-and-Fire Neurons
- Bio-inspired Neuromorphic System
- Sound Source Localization