16th Annual Conference of the International Speech Communication Association

Dresden, Germany
September 6-10, 2015

Convolutional Neural Networks for Small-Footprint Keyword Spotting

Tara N. Sainath, Carolina Parada

Google, USA

We explore using Convolutional Neural Networks (CNNs) for a small-footprint keyword spotting (KWS) task. CNNs are attractive for KWS since they have been shown to outperform DNNs with far fewer parameters. We consider two different applications in our work, one where we limit the number of multiplications of the KWS system, and another where we limit the number of parameters. We present new CNN architectures to address the constraints of each applications. We find that the CNN architectures offer between a 27-44% relative improvement in false reject rate compared to a DNN, while fitting into the constraints of each application.

Full Paper

Bibliographic reference.  Sainath, Tara N. / Parada, Carolina (2015): "Convolutional neural networks for small-footprint keyword spotting", In INTERSPEECH-2015, 1478-1482.