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

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.

arXiv comment3 pages, 2 figures

Cited by in corpus (11)

• Recent Advances in Deep Learning: An Overview
• Learning Efficient Representations for Keyword Spotting with Triplet Loss
• Neural Architecture Search For Keyword Spotting
• EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edge
• TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
• Deep Residual Learning for Small-Footprint Keyword Spotting
• A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
• Ultra-Low Power Keyword Spotting at the Edge
• Howl: A Deployed, Open-Source Wake Word Detection System
• An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting
• Mobiprox: Supporting Dynamic Approximate Computing on Mobiles