Exploring the multidimensional representation of individual speech acoustic parameters extracted by deep unsupervised models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Exploring the multidimensional representation of individual speech acoustic parameters extracted by deep unsupervised models

Résumé

Understanding latent representations of speech by unsupervised models enables powerful signal analysis, transformation, and generation. Numerous studies have identified directions of variation of acoustic features such as fundamental frequency or formants in unsupervised models latent spaces, but it is yet not well understood why the variation of such one-dimensional features is often explained by multiple latent dimensions. This paper proposes a methodology for interpreting these dimensions, in the latent space of a variational autoencoder trained on a multi-speaker database.
Fichier principal
Vignette du fichier
jacquelin23_ssw.pdf (175.94 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04274170 , version 1 (07-11-2023)

Identifiants

  • HAL Id : hal-04274170 , version 1

Citer

Maxime Jacquelin, Maëva Garnier, Laurent Girin, Rémy Vincent, Olivier Perrotin. Exploring the multidimensional representation of individual speech acoustic parameters extracted by deep unsupervised models. SSW 2023 - 12th ISCA Speech Synthesis Workshop (SSW2023), Aug 2023, Grenoble, France. pp.240-241. ⟨hal-04274170⟩
51 Consultations
20 Téléchargements

Partager

Gmail Facebook X LinkedIn More