Abstract

Keyword spotting (or wake-word detection) establishes a major component of human–machine interactions. Maximizing the detection accuracy at a low false alarm rate, while minimizing the footprint size and computation are the goals of keyword spotting systems. To better satisfy these requirements, we propose an end-to-end neural architecture with deformable convolution combined with the attention mechanism. The deformable convolution layer drives the model to focus more on the human speech region, while the attention mechanism further focuses on the most important part of the speech segment for keyword spotting. Our experimental results on real-world dataset “Hey Snips” show that our system significantly outperforms recent approaches in terms of quality of detection and size and complexity. With only 78 K parameters, the model achieves a false rejection rate (FRR) of 0.005% on clean samples, and 0.531% in noisy conditions, at 0.5 false alarm (FA) per hour.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call