Feasibility of constructing an expressive speech corpus from television soap opera dialogue

Author(s):  
Peter Rutten
2009 ◽  
Vol 51 (9) ◽  
pp. 744-758 ◽  
Author(s):  
Ignasi Iriondo ◽  
Santiago Planet ◽  
Joan-Claudi Socoró ◽  
Elisa Martínez ◽  
Francesc Alías ◽  
...  

2015 ◽  
Vol 101 (5) ◽  
pp. 1052-1063 ◽  
Author(s):  
L. Demri ◽  
L. Falek ◽  
H. Teffahi

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Carlos Monzo ◽  
Ignasi Iriondo ◽  
Joan Claudi Socoró

This paper presents the perceptual experiments that were carried out in order to validate the methodology of transforming expressive speech styles using voice quality (VoQ) parameters modelling, along with the well-known prosody (F0, duration, and energy), from a neutral style into a number of expressive ones. The main goal was to validate the usefulness of VoQ in the enhancement of expressive synthetic speech in terms of speech quality and style identification. A harmonic plus noise model (HNM) was used to modify VoQ and prosodic parameters that were extracted from an expressive speech corpus. Perception test results indicated the improvement of obtained expressive speech styles using VoQ modelling along with prosodic characteristics.


Author(s):  
Ji-Eun Lee ◽  
Wook-Eun Kim ◽  
Kwang Hyun Kim ◽  
Myung-Whun Sung ◽  
Tack-Kyun Kwon

Sign in / Sign up

Export Citation Format

Share Document