Multi-Task Learning and Weighted Cross-Entropy for DNN-Based Keyword Spotting

Sankaran Panchapagesan, Ming Sun, Aparna Khare, Spyros Matsoukas, Arindam Mandal, Björn Hoffmeister, Shiv Vitaladevuni


We propose improved Deep Neural Network (DNN) training loss functions for more accurate single keyword spotting on resource-constrained embedded devices. The loss function modifications consist of a combination of multi-task training and weighted cross entropy. In the multi-task architecture, the keyword DNN acoustic model is trained with two tasks in parallel — the main task of predicting the keyword-specific phone states, and an auxiliary task of predicting LVCSR senones. We show that multi-task learning leads to comparable accuracy over a previously proposed transfer learning approach where the keyword DNN training is initialized by an LVCSR DNN of the same input and hidden layer sizes. The combination of LVCSR-initialization and Multi-task training gives improved keyword detection accuracy compared to either technique alone. We also propose modifying the loss function to give a higher weight on input frames corresponding to keyword phone targets, with a motivation to balance the keyword and background training data. We show that weighted cross-entropy results in additional accuracy improvements. Finally, we show that the combination of 3 techniques — LVCSR-initialization, multi-task training and weighted cross-entropy gives the best results, with significantly lower False Alarm Rate than the LVCSR-initialization technique alone, across a wide range of Miss Rates.


DOI: 10.21437/Interspeech.2016-1485

Cite as

Panchapagesan, S., Sun, M., Khare, A., Matsoukas, S., Mandal, A., Hoffmeister, B., Vitaladevuni, S. (2016) Multi-Task Learning and Weighted Cross-Entropy for DNN-Based Keyword Spotting. Proc. Interspeech 2016, 760-764.

Bibtex
@inproceedings{Panchapagesan+2016,
author={Sankaran Panchapagesan and Ming Sun and Aparna Khare and Spyros Matsoukas and Arindam Mandal and Björn Hoffmeister and Shiv Vitaladevuni},
title={Multi-Task Learning and Weighted Cross-Entropy for DNN-Based Keyword Spotting},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-1485},
url={http://dx.doi.org/10.21437/Interspeech.2016-1485},
pages={760--764}
}