On the suitability of vocalic sandwiches in a corpus-based TTS engine

David Guennec 1 Damien Lolive 1
1 EXPRESSION - Expressiveness in Human Centered Data/Media
UBS - Université de Bretagne Sud, IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : Unit selection speech synthesis systems generally rely on target and concatenation costs for selecting the best unit sequence. The role of the concatenation cost is to insure that joining two voice segments will not cause any acoustic artefact to appear. For this task, acoustic distances (MFCC, F0) are typically used but in many cases, this is not enough to prevent concatenation artefacts. Among other strategies, the improvement of corpus covering by favouring units that naturally support well the joining process (vocalic sandwiches) seems to be effective on TTS. In this paper, we investigate if vocalic sandwiches can be used directly in the unit selection engine when the corpus was not created using that principle. First, the sandwich approach is directly transposed in the unit selection engine with a penalty that greatly favours concatenation on sandwich boundaries. Second, a derived fuzzy version is proposed to relax the penalty based on the concatenation cost, with respect to the cost distribution. We show that the sandwich approach, very efficient at the corpus creation step, seems to be inefficient when directly transposed in the unit selection engine. However, we observe that the fuzzy approach enhances synthesis quality, especially on sentences with high concatenation costs.
Type de document :
Communication dans un congrès
Interspeech, Sep 2016, San Francisco, United States. 2016
Liste complète des métadonnées

https://hal.inria.fr/hal-01338839
Contributeur : Damien Lolive <>
Soumis le : mercredi 29 juin 2016 - 11:43:37
Dernière modification le : jeudi 15 novembre 2018 - 11:58:49

Identifiants

  • HAL Id : hal-01338839, version 1

Citation

David Guennec, Damien Lolive. On the suitability of vocalic sandwiches in a corpus-based TTS engine. Interspeech, Sep 2016, San Francisco, United States. 2016. 〈hal-01338839〉

Partager

Métriques

Consultations de la notice

526