Papers › Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting

Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting

18 Oct 2017arXiv:1710.06554archive 2025-07-28

Raphael Tang, Jimmy Lin

We describe Honk, an open-source PyTorch reimplementation of convolutional neural networks for keyword spotting that are included as examples in TensorFlow. These models are useful for recognizing "command triggers" in speech-based interfaces (e.g., "Hey Siri"), which serve as explicit cues for audio recordings of utterances that are sent to the cloud for full speech recognition. Evaluation on Google's recently released Speech Commands Dataset shows that our reimplementation is comparable in accuracy and provides a starting point for future work on the keyword spotting task.

PaperPDFCode

Code

castorini/honk officialmentioned in papermentioned on GitHubpytorchMIT report
etosworld/etos-keywordspotting mentioned on GitHubtf report
magahub/honk mentioned on GitHubpytorchMIT report
magahub/honknew 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 SpottingSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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