Laika: A 5uW Programmable LSTM Accelerator for Always-on Keyword Spotting in 65nm CMOS
Authors:
- 1 September 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 166-169
Abstract
The ubiquitous importance of speech recognition for diverse applications in mobile devices, necessitates its low power embedded execution. Often, a Keyword Spotting System (KWS) is used to detect specific wake-up words spoken by a user, as a simple user interface, or front-end layer to a larger speech recognition system. Yet, such KWS must be always active, hence imposing strict power and latency constraints. While deep learning algorithms like Long Short-Term Memory (LSTM) demonstrated excellent KWS accuracies, current implementations fail to fit in the tight embedded memory and power budgets. This paper presents Laika: the implementation of a KWS system using an LSTM accelerator designed in 65nm CMOS. For this application, an LSTM model is trained through a speech database and deployed on our custom, yet highly programmable LSTM accelerator. Approximate computing techniques further reduce power consumption, while maintaining high accuracy and reliability. Experimental results demonstrate a power consumption of less than 5μW for real-time KWS applications.Keywords
This publication has 6 references indexed in Scilit:
- OCEAN: An on-chip incremental-learning enhanced processor with gated recurrent neural network accelerators2017
- 14.7 A 288µW programmable deep-learning processor with 270KB on-chip weight storage using non-uniform memory hierarchy for mobile intelligence2017
- Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting2017
- 14.4 A scalable speech recognizer with deep-neural-network acoustic models and voice-activated power gating2017
- EIE: Efficient Inference Engine on Compressed Deep Neural Network2016
- Online word-spotting in continuous speech with recurrent neural networks2014