This book focuses on the automatic speech synthesis field, and more specifically on unit selection. A deep analysis and a diagnosis of the unit selection algorithm (a lattice search algorithm) is provided. The importance of having the optimal solution is discussed and a new unit selection implementation based on a A* algorithm is presented. The IRISA TTS system, built for the study, is also presented. Three cost function enhancements are also presented. The first one is a new way ¿ in the target cost ¿ to minimize important spectral differences by selecting sequences of candidate units that minimize a mean cost instead of an absolute one. This cost is tested on a phonemic duration distance but is applicable to others. Our second proposition is a target sub-cost addressing intonation. It is based on coefficients extracted through a generalized version of Fujisaki¿s command-response model. This model features gamma functions modeling F0 called atoms. Finally, our third contribution concerns a penalty system that aims at enhancing the concatenation cost. This system is tempered by a fuzzy function that allows to soften penalties for units presenting low concatenation costs.
| Autorius: | David Guennec |
| Leidėjas: | Éditions universitaires européennes |
| Išleidimo metai: | 2017 |
| Knygos puslapių skaičius: | 288 |
| ISBN-10: | 3639560329 |
| ISBN-13: | 9783639560329 |
| Formatas: | 220 x 150 x 18 mm. Knyga minkštu viršeliu |
| Kalba: | Anglų |
Parašykite atsiliepimą apie „Study of Unit Selection Text-To-Speech Synthesis Algorithms“
