Progressive Voice Trigger Detection: Accuracy vs Latency
This work addresses latency-accuracy trade-offs for virtual assistants, presenting an incremental improvement over existing methods.
The paper tackles the trade-off between accuracy and latency in voice trigger detection by exploiting audio context after the trigger phrase, showing that delaying decisions for 3% of true triggers yields a 66% relative improvement in false rejection rate with negligible latency increase.
We present an architecture for voice trigger detection for virtual assistants. The main idea in this work is to exploit information in words that immediately follow the trigger phrase. We first demonstrate that by including more audio context after a detected trigger phrase, we can indeed get a more accurate decision. However, waiting to listen to more audio each time incurs a latency increase. Progressive Voice Trigger Detection allows us to trade-off latency and accuracy by accepting clear trigger candidates quickly, but waiting for more context to decide whether to accept more marginal examples. Using a two-stage architecture, we show that by delaying the decision for just 3% of detected true triggers in the test set, we are able to obtain a relative improvement of 66% in false rejection rate, while incurring only a negligible increase in latency.