Representation Learning for Discovering Phonemic Tone Contours

Bai Li, Jing Yi Xie, Frank Rudzicz


Abstract
Tone is a prosodic feature used to distinguish words in many languages, some of which are endangered and scarcely documented. In this work, we use unsupervised representation learning to identify probable clusters of syllables that share the same phonemic tone. Our method extracts the pitch for each syllable, then trains a convolutional autoencoder to learn a low-dimensional representation for each contour. We then apply the mean shift algorithm to cluster tones in high-density regions of the latent space. Furthermore, by feeding the centers of each cluster into the decoder, we produce a prototypical contour that represents each cluster. We apply this method to spoken multi-syllable words in Mandarin Chinese and Cantonese and evaluate how closely our clusters match the ground truth tone categories. Finally, we discuss some difficulties with our approach, including contextual tone variation and allophony effects.
Anthology ID:
2020.sigmorphon-1.26
Volume:
Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | SIGMORPHON | WS
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
217–223
Language:
URL:
https://aclanthology.org/2020.sigmorphon-1.26
DOI:
10.18653/v1/2020.sigmorphon-1.26
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.sigmorphon-1.26.pdf
Video:
 http://slideslive.com/38929879