Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition

Frontiers in Neuroscience

Kay Chen Tan¹  Malu Zhang²  Emre Yılmaz²  Jibin Wu²  Haizhou Li³ 

[1] Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong;Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore;Faculty for Computer Science and Mathematics, University of Bremen, Bremen, Germany;

关键词: deep spiking neural networks;    automatic speech recognition;    tandem learning;    neuromorphic computing;    acoustic modeling;   

DOI  :  10.3389/fnins.2020.00199

来源: DOAJ

【 摘 要 】

Artificial neural networks (ANN) have become the mainstream acoustic modeling technique for large vocabulary automatic speech recognition (ASR). A conventional ANN features a multi-layer architecture that requires massive amounts of computation. The brain-inspired spiking neural networks (SNN) closely mimic the biological neural networks and can operate on low-power neuromorphic hardware with spike-based computation. Motivated by their unprecedented energy-efficiency and rapid information processing capability, we explore the use of SNNs for speech recognition. In this work, we use SNNs for acoustic modeling and evaluate their performance on several large vocabulary recognition scenarios. The experimental results demonstrate competitive ASR accuracies to their ANN counterparts, while require only 10 algorithmic time steps and as low as 0.68 times total synaptic operations to classify each audio frame. Integrating the algorithmic power of deep SNNs with energy-efficient neuromorphic hardware, therefore, offer an attractive solution for ASR applications running locally on mobile and embedded devices.

【 授权许可】

Unknown