Voice Onset Time (VOT), a key measurement of speech for basic research and applied medical studies, is the time between the onset of a stop burst and the onset of voicing. When the voicing onset precedes burst onset the VOT is negative; if voicing onset follows the burst, it is positive. In this work, we present a deep-learning model for accurate and reliable measurement of VOT in naturalistic speech. The proposed system addresses two critical issues: it can measure positive and negative VOT equally well, and it is trained to be robust to variation across annotations. Our approach is based on the structured prediction framework, where the feature functions are defined to be RNNs. These learn to capture segmental variation in the signal. Results suggest that our method substantially improves over the current state-of-the-art. In contrast to previous work, our Deep and Robust VOT annotator, Dr.VOT, can successfully estimate negative VOTs while maintaining state-of-the-art performance on positive VOTs. This high level of performance generalizes to new corpora without further retraining.
|Number of pages||5|
|Journal||Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH|
|State||Published - 2019|
|Event||20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 - Graz, Austria|
Duration: 15 Sep 2019 → 19 Sep 2019
Bibliographical noteFunding Information:
Research supported in part by NIH grant 1R21HD077140. Thanks to Olga Dmitrieva and Alexander Francis for providing access to VOT datasets.
Copyright © 2019 ISCA
- Adversarial training
- Multi-task learning
- Recurrent neural networks
- Sequence segmentation
- Structured prediction