Title :
Articulatory features for expressive speech synthesis
Author :
Black, Alan W. ; Bunnell, H. Timothy ; Dou, Ying ; Muthukumar, Prasanna Kumar ; Metze, Florian ; Perry, Daniel ; Polzehl, Tim ; Prahallad, Kishore ; Steidl, Stefan ; Vaughn, Callie
Author_Institution :
Language Technol. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
This paper describes some of the results from the project entitled “New Parameterization for Emotional Speech Synthesis” held at the Summer 2011 JHU CLSP workshop. We describe experiments on how to use articulatory features as a meaningful intermediate representation for speech synthesis. This parameterization not only allows us to reproduce natural sounding speech but also allows us to generate stylistically varying speech.
Keywords :
speech synthesis; New Parameterization for Emotional Speech Synthesis; Summer 2011 JHU CLSP workshop; articulatory features; clean speech databases; crowd-sourcing; emotion identification; expressive speech synthesis; natural sounding speech reconstruction; stylistically varying speech; Conferences; Databases; Feature extraction; Hidden Markov models; Humans; Speech; Speech synthesis; articulatory features; emotional speech; evaluation; meta-data extraction; speech synthesis;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6288796
