Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition

Jibin Wu, Emre Yılmaz, Malu Zhang, Haizhou Li, Kay Chen Tan

Research output: Journal article publicationJournal articleAcademic researchpeer-review

60 Citations (Scopus)


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.

Original languageEnglish
Article number199
Pages (from-to)1-14
JournalFrontiers in Neuroscience
Publication statusPublished - 17 Mar 2020
Externally publishedYes


  • acoustic modeling
  • automatic speech recognition
  • deep spiking neural networks
  • neuromorphic computing
  • tandem learning

ASJC Scopus subject areas

  • General Neuroscience


Dive into the research topics of 'Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition'. Together they form a unique fingerprint.

Cite this