Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting

Sercan Ö. Arık, Markus Kliegl, Rewon Child, Joel Hestness, Andrew Gibiansky, Chris Fougner, Ryan Prenger, Adam Coates


Keyword spotting (KWS) constitutes a major component of human-technology interfaces. Maximizing the detection accuracy at a low false alarm (FA) rate, while minimizing the footprint size, latency and complexity are the goals for KWS. Towards achieving them, we study Convolutional Recurrent Neural Networks (CRNNs). Inspired by large-scale state-of-the-art speech recognition systems, we combine the strengths of convolutional layers and recurrent layers to exploit local structure and long-range context. We analyze the effect of architecture parameters, and propose training strategies to improve performance. With only ~230k parameters, our CRNN model yields acceptably low latency, and achieves 97.71% accuracy at 0.5 FA/hour for 5 dB signal-to-noise ratio.


 DOI: 10.21437/Interspeech.2017-1737

Cite as: Arık, S.Ö., Kliegl, M., Child, R., Hestness, J., Gibiansky, A., Fougner, C., Prenger, R., Coates, A. (2017) Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting. Proc. Interspeech 2017, 1606-1610, DOI: 10.21437/Interspeech.2017-1737.


@inproceedings{Arık2017,
  author={Sercan Ö. Arık and Markus Kliegl and Rewon Child and Joel Hestness and Andrew Gibiansky and Chris Fougner and Ryan Prenger and Adam Coates},
  title={Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={1606--1610},
  doi={10.21437/Interspeech.2017-1737},
  url={http://dx.doi.org/10.21437/Interspeech.2017-1737}
}