Corpus design for expressive speech: impact of the utterance length - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Corpus design for expressive speech: impact of the utterance length

Résumé

Voice corpus plays a crucial role in the quality of the synthetic speech generation, specially under a length constraint. Creating a new voice is costly and the recording script selection for an expressive TTS task is generally considered as an optimization problem in order to achieve a rich and parsimonious corpus. In order to vocalize a given book using a TTS system, we investigate four script selection approaches. Based on preliminary observations, we simply propose to select shortest utterances of the book and compare the achievements of this method with state of the art ones for two books, with different utterance lengths and styles, using two kinds of concatenation based TTS systems. The study of the TTS costs indicates that selecting the shortest utterances could result in better synthetic quality, which is confirmed by a perceptual test. By investigating usual criteria for corpus design in literature like unit coverage or distribution similarity of units, it turns out that they are not pertinent metrics in the framework of this study.
Fichier principal
Vignette du fichier
199.pdf (497.76 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02874005 , version 1 (18-06-2020)

Identifiants

Citer

Meysam Shamsi, Jonathan Chevelu, Nelly Barbot, Damien Lolive. Corpus design for expressive speech: impact of the utterance length. 10th International Conference on Speech Prosody 2020, May 2020, Tokyo, Japan. pp.955-959, ⟨10.21437/SpeechProsody.2020-195⟩. ⟨hal-02874005⟩
136 Consultations
207 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More