Tom Véniat

2 accepted papers

2019

Stochastic Adaptive Neural Architecture Search for Keyword Spotting

Tom Véniat, Olivier Schwander, Ludovic Denoyer

ICASSP 2019accepted

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 lev…

Cited by 0 Source ↗Scholar ↗

2018

Learning Time/Memory-Efficient Deep Architectures With Budgeted Super Networks

Tom Véniat, Ludovic Denoyer

CVPR 2018poster

We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost. For instance, our approach is able to solve the following tasks: learn a neural network able to predict well in less than 100 milliseconds or learn an efficient mode…

Cited by 108 Source ↗PDF ↗code ↗Scholar ↗