Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting
This provides an open-source tool for researchers and developers working on keyword spotting, but it is incremental as it reimplements existing models without introducing new methods.
The authors tackled the problem of keyword spotting for speech-based interfaces by reimplementing existing convolutional neural networks from TensorFlow into PyTorch, achieving comparable accuracy on Google's Speech Commands Dataset.
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.