Descripción
|
|
---|---|
2015AbstractThis paper proposes an emotion transplantation method capable of modifying a synthetic speech model through the use ofCSMAPLR adaptation in order to incorporate emotional information learned from a different speaker model while maintaining theidentity of the original speaker as much as possible. The proposed method relies on learning both emotional and speaker identityinformation by means of their adaptation function from an average voice model, and combining them into a single cascade transformcapable of imbuing the desired emotion into the target speaker. This method is then applied to the task of transplanting four emotions(anger, happiness, sadness and surprise) into 3 male speakers and 3 female speakers and evaluated in a number of perceptual tests.The results of the evaluations show how the perceived naturalness for emotional text significantly favors the use of the proposedtransplanted emotional speech synthesis when compared to traditional neutral speech synthesis, evidenced by a big increase inthe perceived emotional strength of the synthesized utterances at a slight cost in speech quality. A final evaluation with a roboticlaboratory assistant application shows how by using emotional speech we can significantly increase the students? satisfaction withthe dialog system, proving how the proposed emotion transplantation system provides benefits in real applications.© 2015 Elsevier Ltd. All rights reserved. | |
Internacional
|
Si |
JCR del ISI
|
Si |
Título de la revista
|
Computer Speech And Language |
ISSN
|
0885-2308 |
Factor de impacto JCR
|
1,753 |
Información de impacto
|
|
Volumen
|
34 |
DOI
|
10.1016/j.csl.2015.03.008 |
Número de revista
|
1 |
Desde la página
|
292 |
Hasta la página
|
307 |
Mes
|
SIN MES |
Ranking
|
Journal Rank in Category 47/123 |