DocumentCode
3715857
Title
Breath and repeat: An attempt at enhancing speech-laugh synthesis quality
Author
Kevin El Haddad;Huseyin Çakmak;Stéphane Dupont;Thierry Dutoit
Author_Institution
University of Mons (UMONS) - TCTS Lab
fYear
2015
Firstpage
355
Lastpage
358
Abstract
In this work, we present a study dedicated to improve the speech-laugh synthesis quality. The impact of two factors is evaluated. The first factor is the addition of breath intake sounds after laughter bursts in speech. The second is the repetition of the word interrupted by laughs in the speech-laugh sentences. Several configurations are evaluated through subjective perceptual tests. We report an improvement of the synthesized speech-laugh naturalness when the breath intake sounds are added. We were unable, though, to make a conclusion concerning a possible positive impact of the repetition of the interrupted words on the speech-laugh synthesis quality.
Keywords
"Hidden Markov models","Speech","Acoustics","Databases","Signal processing","Bismuth","Europe"
Publisher
ieee
Conference_Titel
Signal Processing Conference (EUSIPCO), 2015 23rd European
Electronic_ISBN
2076-1465
Type
conf
DOI
10.1109/EUSIPCO.2015.7362404
Filename
7362404
Link To Document