Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting
Published in
arXiv.org(2017)External Links:
TL
TL;DR
Honk, an open-source PyTorch reimplementation of convolutional neural networks for keyword spotting that are included as examples in TensorFlow, is described and provides a starting point for future work on the keyword spotting task.
Abstract
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.
References3 items
1
Launching the Speech Commands Dataset
2
Google had to disable a feature on its new $50 smart speaker after the gadget listened in on some users
3