STOCHASTIC ADAPTIVE NEURAL ARCHITECTURE SEARCH FOR KEYWORD SPOTTING - Sorbonne Université Access content directly
Conference Papers Year : 2019

STOCHASTIC ADAPTIVE NEURAL ARCHITECTURE SEARCH FOR KEYWORD SPOTTING

Abstract

The problem of keyword spotting i.e. identifying keywords in a real-time audio stream is mainly solved by applying a neural network over successive sliding windows. Due to the difficulty of the task, baseline models are usually large, resulting in a high computational cost and energy consumption level. We propose a new method called SANAS (Stochastic Adaptive Neural Architecture Search) which is able to adapt the architecture of the neural network on-the-fly at inference time such that small architectures will be used when the stream is easy to process (silence, low noise, ...) and bigger networks will be used when the task becomes more difficult. We show that this adaptive model can be learned end-to-end by optimizing a trade-off between the prediction performance and the average computational cost per unit of time. Experiments on the Speech Commands dataset [1] show that this approach leads to a high recognition level while being much faster (and/or energy saving) than classical approaches where the network architecture is static.
Fichier principal
Vignette du fichier
ICASSP_2019.pdf (299.87 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02063698 , version 1 (11-03-2019)

Identifiers

Cite

Tom Véniat, Olivier Schwander, Ludovic Denoyer. STOCHASTIC ADAPTIVE NEURAL ARCHITECTURE SEARCH FOR KEYWORD SPOTTING. ICASSP 2019 - International Conference on Acoustics, Speech, and Signal Processing, May 2019, Brighton, United Kingdom. ⟨hal-02063698⟩
124 View
215 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More