Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition
This provides an energy-efficient solution for ASR applications on mobile and embedded devices, though it is incremental as it adapts SNNs to an existing domain.
The paper tackles the high computational cost of conventional artificial neural networks (ANNs) in large vocabulary automatic speech recognition (ASR) by exploring deep spiking neural networks (SNNs), achieving competitive ASR accuracies with significantly reduced computational cost and inference time.
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 energyefficiency 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 significantly reduced computational cost and inference time. 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.