We present a cascade architecture for keyword spotting with speaker verification on mobile devices. By pairing a small computational footprint with specialized digital signal processing (DSP) chips, we are able to achieve low power consumption while continuously listening for a keyword.
- Pub Date:
- December 2017
- Computer Science - Sound;
- Electrical Engineering and Systems Science - Audio and Speech Processing
- 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA