Combining vocal tract length normalization with hierarchial linear transformations

L. Saheer, J. Yamagishi, P.N. Garner, J. Dines

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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 a posteriori linear regression (CSMAPLR) adaptation is presented. Experiments show that the resulting transformation has improved speech quality with better naturalness, intelligibility and improved speaker similarity.
Original languageEnglish
Title of host publicationAcoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Number of pages4
Publication statusPublished - 1 Mar 2012

Keywords / Materials (for Non-textual outputs)

  • Bayes methods
  • speech intelligibility
  • CSMAPLR adaptation
  • MLLR based adaptation technique
  • constrained structural maximum a posteriori linear regression
  • hierarchial Bayesian framework
  • hierarchial linear transformation
  • intelligibility
  • rapid adaptation technique
  • speaker similarity
  • statistical parametric speech synthesis
  • vocal tract length normalization
  • Adaptation models
  • Estimation
  • Hidden Markov models
  • Speech
  • Speech synthesis
  • Transforms
  • Vectors
  • Statistical parametric speech synthesis
  • hidden Markov models
  • speaker adaptation


Dive into the research topics of 'Combining vocal tract length normalization with hierarchial linear transformations'. Together they form a unique fingerprint.

Cite this