Always-On Speech Recognition Using TrueNorth, a Reconfigurable, Neurosynaptic Processor

Wei Yu Tsai, Davis R. Barch, Andrew S. Cassidy, Michael V. Debole, Alexander Andreopoulos, Bryan L. Jackson, Myron D. Flickner, John V. Arthur, Dharmendra S. Modha, John Sampson, Vijaykrishnan Narayanan

Research output: Contribution to journalArticle

11 Scopus citations

Abstract

Deep neural networks (DNN) have been shown to be very effective at solving challenging problems in several areas of computing, including vision, speech, and natural language processing. However, traditional platforms for implementing these DNNs are often very power hungry, which has lead to significant efforts in the development of configurable platforms capable of implementing these DNNs efficiently. One of these platforms, the IBM TrueNorth processor, has demonstrated very low operating power in performing visual computing and neural network classification tasks in real-Time. The neuron computation, synaptic memory, and communication fabrics are all configurable, so that a wide range of network types and topologies can be mapped to TrueNorth. This reconfigurability translates into the capability to support a wide range of low-power functions in addition to feed-forward DNN classifiers, including for example, the audio processing functions presented here.In this work, we propose an end-To-end audio processing pipeline that is implemented entirely on a TrueNorth processor and designed to specifically leverage the highly-parallel, low-precision computing primitives TrueNorth offers. As part of this pipeline, we develop an audio feature extractor (LATTE) designed for implementation on TrueNorth, and explore the tradeoffs among several design variants in terms of accuracy, power, and performance. We customize the energy-efficient deep neuromorphic networks structures that our design utilizes as the classifier and show how classifier parameters can trade between power and accuracy. In addition to enabling a wide range of diverse functions, the reconfigurability of TrueNorth enables re-Training and re-programming the system to satisfy varying energy, speed, area, and accuracy requirements. The resulting system's end-To-end power consumption can be as low as 14.43 mW , which would give up to 100 hours of continuous usage with button cell batteries (CR3023 1.5 Whr ) or 450 hours with cellphone batteries (iPhone 6s $6.55 Whr ).

Original languageEnglish (US)
Article number7750640
Pages (from-to)996-1007
Number of pages12
JournalIEEE Transactions on Computers
Volume66
Issue number6
DOIs
StatePublished - Jun 1 2017

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computational Theory and Mathematics

Cite this

Tsai, W. Y., Barch, D. R., Cassidy, A. S., Debole, M. V., Andreopoulos, A., Jackson, B. L., Flickner, M. D., Arthur, J. V., Modha, D. S., Sampson, J., & Narayanan, V. (2017). Always-On Speech Recognition Using TrueNorth, a Reconfigurable, Neurosynaptic Processor. IEEE Transactions on Computers, 66(6), 996-1007. [7750640]. https://doi.org/10.1109/TC.2016.2630683