D
David Leroy
Publications - 8
Citations - 1011
David Leroy is an academic researcher. The author has contributed to research in topics: Keyword spotting & Spoken language. The author has an hindex of 7, co-authored 8 publications receiving 623 citations.
Papers
More filters
Posted Content
Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
Alice Coucke,Alaa Saade,Adrien Ball,Theodore Bluche,Alexandre Caulier,David Leroy,Clément Doumouro,Thibault Gisselbrecht,Francesco Caltagirone,Thibaut Lavril,Maël Primet,Joseph Dureau +11 more
TL;DR: The machine learning architecture of the Snips Voice Platform is presented, a software solution to perform Spoken Language Understanding on microprocessors typical of IoT devices that is fast and accurate while enforcing privacy by design, as no personal user data is ever collected.
Proceedings ArticleDOI
Federated Learning for Keyword Spotting
TL;DR: In this article, a federated averaging algorithm for the "Hey Snips" wake word based on a crowdsourced dataset that mimics a federation of wake word users is proposed.
Proceedings ArticleDOI
Efficient Keyword Spotting Using Dilated Convolutions and Gating
Alice Coucke,Mohammed Chlieh,Thibault Gisselbrecht,David Leroy,Mathieu Poumeyrol,Thibaut Lavril +5 more
TL;DR: A model inspired by the recent success of dilated convolutions in sequence modeling applications, allowing to train deeper architectures in resource-constrained configurations, and applies a custom target labeling that back-propagates loss from specific frames of interest, therefore yielding higher accuracy and only requiring to detect the end of the keyword.
Posted Content
Federated Learning for Keyword Spotting
TL;DR: An extensive empirical study of the federated averaging algorithm for the "Hey Snips" wake word based on a crowdsourced dataset that mimics a federation of wake word users shows that using an adaptive averaging strategy inspired from Adam highly reduces the number of communication rounds required to reach the target performance.
Posted Content
Spoken Language Understanding on the Edge
Alaa Saade,Alice Coucke,Alexandre Caulier,Joseph Dureau,Adrien Ball,Theodore Bluche,David Leroy,Clément Doumouro,Thibault Gisselbrecht,Francesco Caltagirone,Thibaut Lavril,Maël Primet +11 more
TL;DR: The design of an embedded, private-by-design SLU system is outlined and it is shown that it has performance on-par with cloud-based commercial solutions.