We propose an audio-based wakeword-independent verification model to determine whether a wakeword spotting model correctly woke and should respond or incorrectly woke and should not respond. Our model works on any wakeword-initiated audio, independent of the wakeword by operating only on the audio surrounding the wakeword, yielding a wakeword agnostic model. This model is based on two key assumptions: that audio surrounding the wakeword is informative to determine if the user intended to wake the device and that this audio is independent of the wakeword itself. We show experimentally that on wakewords not included in the training set, our model trained without examples or knowledge of the wakeword is able to achieve verification performance comparable to models trained on 5,000 to 10,000 annotated examples of the new wakeword.
Cite as: Wang, J., Kumar, R., Rodehorst, M., Kulis, B., Vitaladevuni, S.N.P. (2020) An Audio-Based Wakeword-Independent Verification System. Proc. Interspeech 2020, 1952-1956, doi: 10.21437/Interspeech.2020-1843
@inproceedings{wang20s_interspeech,
author={Joe Wang and Rajath Kumar and Mike Rodehorst and Brian Kulis and Shiv Naga Prasad Vitaladevuni},
title={{An Audio-Based Wakeword-Independent Verification System}},
year=2020,
booktitle={Proc. Interspeech 2020},
pages={1952--1956},
doi={10.21437/Interspeech.2020-1843}
}