COMBINING VOCAL TRACT LENGTH NORMALIZATION WITH HIERARCHIAL LINEAR TRANSFORMATIONS

Recent research has demonstrated the effectiveness of vocal tract length normalization (VTLN) as a rapid adaptation technique for statistical parametric speech synthesis. VTLN produces speech with naturalness preferable to that of MLLR based adaptation techniques, being much closer in quality to that generated by the original average voice model. However with only a single parameter, VTLN captures very few speaker specific characteristics when compared to linear transform based adaptation techniques. This paper proposes that the merits of VTLN can be combined with those of linear transform based adaptation in a hierarchial Bayesian framework, where VTLN is used as the prior information. A novel technique for propagating the gender information from the VTLN prior through constrained structural maximum aposteriori linear regression (CSMAPLR) adaptation is presented. Experiments show that the resulting transformation has improved speech quality with better naturalness, intelligibility and improved speaker similarity.


Présenté à:
Proceedings in International conference on Speech and Signal processing, Kyoto, Japan
Année
2012
Publisher:
IEEE SPS (ICASSP)
Mots-clefs:
Laboratoires:




 Notice créée le 2013-12-19, modifiée le 2019-08-12

n/a:
Télécharger le documentPDF
Lien externe:
Télécharger le documentRelated documents
Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)