Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition

Conference Paper (2022)
Author(s)

Liming Wang (University of Illinois at Urbana Champaign)

S. Feng (TU Delft - Multimedia Computing)

Mark Hasegawa-Johnson (University of Illinois at Urbana Champaign)

Chang D. Yoo (Korea Advanced Institute of Science and Technology)

Multimedia Computing
More Info
expand_more
Publication Year
2022
Language
English
Multimedia Computing
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. @en
Pages (from-to)
8027-8047
ISBN (electronic)
9781955917216
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Phonemes are defined by their relationship to words: changing a phoneme changes the word. Learning a phoneme inventory with little supervision has been a longstanding challenge with important applications to under-resourced speech technology. In this paper, we bridge the gap between the linguistic and statistical definition of phonemes and propose a novel neural discrete representation learning model for self-supervised learning of phoneme inventory with raw speech and word labels. Given the availability of phoneme segmentation and some mild conditions, we prove that the phoneme inventory learned by our approach converges to the true one with an exponentially low error rate. Moreover, in experiments on TIMIT and Mboshi benchmarks, our approach consistently learns a better phoneme-level representation and achieves a lower error rate in a zero-resource phoneme recognition task than previous state-of-the-art self-supervised representation learning algorithms.

Files

2022.acl-long.553.pdf
(pdf | 4.67 Mb)
- Embargo expired in 28-02-2025
License info not available