DONUT: CTC-based Query-by-Example Keyword Spotting

Published in NeurIPS IRASL Workshop, 2018

Recommended citation: L. Lugosch, S. Myer, and V. S. Tomar, “DONUT: CTC-based query-by-example keyword spotting”, NeurIPS Workshop on Interpretability and Robustness in Audio, Speech, and Language, Montreal, Canada, December 2018.

Train your device to wake up for any phrase you want by recording the phrase three times, estimating the label sequence using a beam search, and computing the log probability of the label sequence at test time using the forward algorithm.