Papers › Efficient keyword spotting using dilated convolutions and gating

Efficient keyword spotting using dilated convolutions and gating

19 Nov 2018arXiv:1811.07684archive 2025-07-28

Alice Coucke, Mohammed Chlieh, Thibault Gisselbrecht, David Leroy, Mathieu Poumeyrol, Thibaut Lavril

We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states. We propose a model inspired by the recent success of dilated convolutions in sequence modeling applications, allowing to train deeper architectures in resource-constrained configurations. Gated activations and residual connections are also added, following a similar configuration to WaveNet. In addition, we apply 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. Our experimental results show that our model outperforms a max-pooling loss trained recurrent neural network using LSTM cells, with a significant decrease in false rejection rate. The underlying dataset - "Hey Snips" utterances recorded by over 2.2K different speakers - has been made publicly available to establish an open reference for wake-word detection.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

snipsco/keyword-spotting-research-datasets mentioned on GitHubNOASSERTION report
snipsco/tract mentioned on GitHubtf report
sonos/keyword-spotting-research-datasets mentioned on GitHubNOASSERTION report
sonos/tract mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Keyword SpottingSmall-Footprint Keyword Spotting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Dilated Causal ConvolutionLSTMMixture of Logistic DistributionsSigmoid ActivationTanh ActivationWaveNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections