Probing phoneme, language and speaker information in unsupervised speech representations

Maureen de Seyssel, Marvin Lavechin, Yossi Adi, Emmanuel Dupoux, Guillaume Wisniewski

Research output: Contribution to journalConference articlepeer-review

9 Scopus citations

Abstract

Unsupervised models of representations based on Contrastive Predictive Coding (CPC) [1] are primarily used in spoken language modelling in that they encode phonetic information. In this study, we ask what other types of information are present in CPC speech representations. We focus on three categories: phone class, gender and language, and compare monolingual and bilingual models. Using qualitative and quantitative tools, we find that both gender and phone class information are present in both types of models. Language information, however, is very salient in the bilingual model only, suggesting CPC models learn to discriminate languages when trained on multiple languages. Some language information can also be retrieved from monolingual models, but it is more diffused across all features. These patterns hold when analyses are carried on the discrete units from a downstream clustering model. However, although there is no effect of the number of target clusters on phone class and language information, more gender information is encoded with more clusters. Finally, we find that there is some cost to being exposed to two languages on a downstream phoneme discrimination task.

Original languageAmerican English
Pages (from-to)1402-1406
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2022-September
DOIs
StatePublished - 2022
Externally publishedYes
Event23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022 - Incheon, Korea, Republic of
Duration: 18 Sep 202222 Sep 2022

Bibliographical note

Publisher Copyright:
Copyright © 2022 ISCA.

Keywords

  • language representation
  • probing
  • self-supervised learning
  • unsupervised speech representation

Fingerprint

Dive into the research topics of 'Probing phoneme, language and speaker information in unsupervised speech representations'. Together they form a unique fingerprint.

Cite this