Role of non-linear data processing on speech recognition task in the framework of reservoir computing

Published

January 15, 2020

Author(s)

Flavio Abreu Araujo, Mathieu Riou, Jacob Torrejon, Sumito Tsunegi, Damien Querlioz, K. Yakushiji, Akio Fukushima, Hitoshi Kubota, Shinji Yuasa, Mark D. Stiles, Julie Grollier

Abstract

The reservoir computing neural network architecture is widely used to test hardware systems for neuromorphic computing. One of the preferred tasks for bench-marking such devices is automatic speech recognition (ASR). However, this task requires acoustic transformations from time domain sound waveforms to frequency domain maps that can be seen as feature extraction techniques. Depending on the method, these may obscure the effect of the hardware. Here, we quantify and separate the contributions of the acoustic transformations and the hardware. The non-linearity in the acoustic transformation plays a critical role in feature extraction as seen in the speech recognition success rate. We compute the gain in word success rate provided by a reservoir computing device, which is an appropriate bench-mark for comparing different hardwares.

Citation

Nature - Scientific Reports

Volume

10

Issue

1

Pub Type

Journals

Download Paper

https://doi.org/10.1038/s41598-019-56991-x

Local Download

Keywords

reservoir computing, spintronics, neuromorphic computing, magnetic tunnel junction, non- linearity, automatic speech recognition

Citation

Abreu Araujo, F. , Riou, M. , Torrejon, J. , Tsunegi, S. , Querlioz, D. , Yakushiji, K. , Fukushima, A. , Kubota, H. , Yuasa, S. , Stiles, M. and Grollier, J. (2020), Role of non-linear data processing on speech recognition task in the framework of reservoir computing, Nature - Scientific Reports, [online], https://doi.org/10.1038/s41598-019-56991-x, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=927619 (Accessed April 20, 2024)