logo Idiap Research Institute        
 [BibTeX] [Marc21]
VTLN Adaptation for Statistical Speech Synthesis
Type of publication: Idiap-RR
Citation: Saheer_Idiap-RR-41-2009
Number: Idiap-RR-41-2009
Year: 2009
Month: 12
Institution: Idiap
Abstract: The advent of statistical speech synthesis has enabled the unification of the basic techniques used in speech synthesis and recognition. Adaptation techniques that have been successfully used in recognition systems can now be applied to synthesis systems to improve the quality of the synthesized speech. The application of vocal tract length normalization (VTLN) for synthesis is explored in this paper. VTLN based adaptation requires estimation of a single warping factor, which can be accurately estimated from very little adaptation data and gives additive improvements over CMLLR adaptation. The challenge of estimating accurate warping factors using higher order features is solved by initializing warping factor estimation with the values calculated from lower order features.
Crossref: Saheer_ICASSP_2010:
Projects Idiap
Authors Saheer, Lakshmi
Garner, Philip N.
Dines, John
Liang, Hui
Added by: [ADM]
Total mark: 0
  • Saheer_Idiap-RR-41-2009.pdf (MD5: 25cea01f1bd9c5c4321087c6594dc1f1)
       (Idiap-RR for ICASSP 2010 paper)