Probing phoneme, language and speaker information in unsupervised speech representations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Probing phoneme, language and speaker information in unsupervised speech representations

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.
Fichier principal
Vignette du fichier
2203.16193.pdf (4.18 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03830470 , version 1 (26-10-2022)

Identifiers

  • HAL Id : hal-03830470 , version 1

Cite

Maureen de Seyssel, Marvin Lavechin, Yossi Adi, Emmanuel Dupoux, Guillaume Wisniewski. Probing phoneme, language and speaker information in unsupervised speech representations. Interspeech 2022 - 23rd INTERSPEECH Conference, Sep 2022, Incheon, South Korea. ⟨hal-03830470⟩
51 View
37 Download

Share

Gmail Mastodon Facebook X LinkedIn More