Voice Passing : a Non-Binary Voice Gender Prediction System for evaluating Transgender voice transition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Voice Passing : a Non-Binary Voice Gender Prediction System for evaluating Transgender voice transition

Résumé

This paper presents a software allowing to describe voices using a continuous Voice Femininity Percentage (VFP). This system is intended for transgender speakers during their voice transition and for voice therapists supporting them in this process. A corpus of 41 French cis-and transgender speakers was recorded. A perceptual evaluation allowed 57 participants to estimate the VFP for each voice. Binary gender classification models were trained on external gender-balanced data and used on overlapping windows to obtain average gender prediction estimates, which were calibrated to predict VFP and obtained higher accuracy than F0 or vocal track length-based models. Training data speaking style and DNN architecture were shown to impact VFP estimation. Accuracy of the models was affected by speakers' age. This highlights the importance of style, age, and the conception of gender as binary or not, to build adequate statistical representations of cultural concepts.
Fichier principal
Vignette du fichier
doukhan23_interspeech.pdf (264.32 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : Copyright (Tous droits réservés)

Dates et versions

hal-04199980 , version 1 (08-09-2023)

Identifiants

Citer

David Doukhan, Simon Devauchelle, Lucile Girard-Monneron, Mía Chávez Ruz, V. Chaddouk, et al.. Voice Passing : a Non-Binary Voice Gender Prediction System for evaluating Transgender voice transition. INTERSPEECH 2023, Naomi Harte; Julie Carson-Berndsen; Gareth Jones, Aug 2023, Dublin, Ireland. pp.5207-5211, ⟨10.21437/interspeech.2023-1835⟩. ⟨hal-04199980⟩
79 Consultations
97 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More