Stochastic Adaptive Neural Architecture Search for Keyword Spotting

11/16/2018
by   Tom Véniat, et al.
8

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 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.

READ FULL TEXT
research
08/04/2021

Efficient Neural Architecture Search with Performance Prediction

Neural networks are powerful models that have a remarkable ability to ex...
research
06/04/2021

Encoder-Decoder Neural Architecture Optimization for Keyword Spotting

Keyword spotting aims to identify specific keyword audio utterances. In ...
research
01/09/2020

Performance-Oriented Neural Architecture Search

Hardware-Software Co-Design is a highly successful strategy for improvin...
research
09/08/2020

AutoKWS: Keyword Spotting with Differentiable Architecture Search

Smart audio devices are gated by an always-on lightweight keyword spotti...
research
09/01/2020

Neural Architecture Search For Keyword Spotting

Deep neural networks have recently become a popular solution to keyword ...
research
11/16/2019

S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

Recently, dynamic inference has emerged as a promising way to reduce the...
research
09/07/2019

A greedy constructive algorithm for the optimization of neural network architectures

In this work we propose a new method to optimize the architecture of an ...

Please sign up or login with your details

Forgot password? Click here to reset