Phonetic Analysis of Self-supervised Representations of English Speech

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We present an analysis of discrete units discovered via self-supervised representation learning on English speech. We focus on units produced by a pre-trained HuBERT model due to its wide adoption in ASR, speech synthesis, and many other tasks. Whereas previous work has evaluated the quality of such quantization models in aggregate over all phones for a given language, we break our analysis down into broad phonetic classes, taking into account specific aspects of their articulation when considering their alignment to discrete units. We find that these units correspond to sub-phonetic events, and that fine dynamics such as the distinct closure and release portions of plosives tend to be represented by sequences of discrete units. Our work provides a reference for the phonetic properties of discrete units discovered by HuBERT, facilitating analyses of many speech applications based on this model.

Original languageEnglish
Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
EditorsHanseok Ko, John H. L. Hansen
PublisherISCA
Pages3583-3587
Number of pages5
Volume2022-September
DOIs
Publication statusPublished - 18 Sept 2022
Event23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022 - Incheon, Korea, Republic of
Duration: 18 Sept 202222 Sept 2022

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
ISSN (Print)2308-457X

Conference

Conference23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022
Country/TerritoryKorea, Republic of
CityIncheon
Period18/09/2222/09/22

Keywords / Materials (for Non-textual outputs)

  • self-supervised learning
  • speech units

Fingerprint

Dive into the research topics of 'Phonetic Analysis of Self-supervised Representations of English Speech'. Together they form a unique fingerprint.

Cite this