DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Liming | ko |
dc.contributor.author | Feng, Siyuan | ko |
dc.contributor.author | Hasegawa-Johnson, Mark | ko |
dc.contributor.author | Yoo, Chang-Dong | ko |
dc.date.accessioned | 2022-11-18T05:02:32Z | - |
dc.date.available | 2022-11-18T05:02:32Z | - |
dc.date.created | 2022-06-25 | - |
dc.date.created | 2022-06-25 | - |
dc.date.created | 2022-06-25 | - |
dc.date.issued | 2022-05-23 | - |
dc.identifier.citation | 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 | - |
dc.identifier.uri | http://hdl.handle.net/10203/299984 | - |
dc.description.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. Under mild assumptions, 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. | - |
dc.language | English | - |
dc.publisher | Association for Computational Linguistics | - |
dc.title | Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition | - |
dc.type | Conference | - |
dc.identifier.wosid | 000828702308011 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 | - |
dc.identifier.conferencecountry | IE | - |
dc.identifier.conferencelocation | Dublin | - |
dc.identifier.doi | 10.18653/v1/2022.acl-long.553 | - |
dc.contributor.localauthor | Yoo, Chang-Dong | - |
dc.contributor.nonIdAuthor | Wang, Liming | - |
dc.contributor.nonIdAuthor | Feng, Siyuan | - |
dc.contributor.nonIdAuthor | Hasegawa-Johnson, Mark | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.