Evaluation of delexicalization methods for research on emotional speech - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Evaluation of delexicalization methods for research on emotional speech

Résumé

Perceptual evaluation of non-controlled emotional speech requires delexicalization to neutralize semantic variation. However, most existing methods imply losing spectral cues crucial to emotional attribution, related to both laryngeal and supralaryngeal settings. We propose a method relying on voice morphing to retain part of the spectral information of the original stimuli, as an additional step to diphone synthesis delexicalization. After previous assessment of intelligibility loss, this study evaluates the naturalness of angry and neutral expressions in French films, delexicalized using low-pass filtering and the proposed method implemented with MBROLA and STRAIGHT. Results show that morphing-based delexicalization, which leads to accurate emotional attribution, is rated with a higher degree of naturalness than low-pass filtering. Implications for research in affective speech are discussed with regards to other delexicalization methods proposed in the literature.
Fichier principal
Vignette du fichier
audibert23_interspeech.pdf (564 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04269206 , version 1 (03-11-2023)

Identifiants

Citer

Nicolas Audibert, Francesca Carbone, Maud Champagne-Lavau, Aurélien Said Housseini, Caterina Petrone. Evaluation of delexicalization methods for research on emotional speech. INTERSPEECH 2023, Aug 2023, Dublin, Ireland. pp.2618-2622, ⟨10.21437/interspeech.2023-1903⟩. ⟨hal-04269206⟩
27 Consultations
35 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More