%Aigaion2 BibTeX export from Idiap Publications
%Sunday 22 December 2024 02:37:12 AM

@INPROCEEDINGS{Saheer_ICASSP_2012,
         author = {Saheer, Lakshmi and Yamagishi, Junichi and Garner, Philip N. and Dines, John},
       keywords = {constrained structural maximum a posteriori linear regression, hidden Markov models, speaker adaptation, Statistical parametric speech synthesis, vocal tract length normalization},
       projects = {Idiap, EMIME},
          month = mar,
          title = {COMBINING VOCAL TRACT LENGTH NORMALIZATION WITH HIERARCHIAL LINEAR TRANSFORMATIONS},
      booktitle = {Proceedings in International conference on Speech and Signal processing},
           year = {2012},
          pages = {4493-4496},
      publisher = {IEEE SPS (ICASSP)},
       location = {Kyoto, Japan},
       crossref = {Saheer_Idiap-RR-11-2012},
       abstract = {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.},
            pdf = {https://publications.idiap.ch/attachments/papers/2012/Saheer_ICASSP_2012.pdf}
}



crossreferenced publications: 
@TECHREPORT{Saheer_Idiap-RR-11-2012,
         author = {Saheer, Lakshmi and Yamagishi, Junichi and Garner, Philip N. and Dines, John},
       projects = {Idiap, EMIME},
          month = {4},
          title = {Combining Vocal Tract Length Normalization with Linear Transformations in a Bayesian Framework},
           type = {Idiap-RR},
         number = {Idiap-RR-11-2012},
           year = {2012},
    institution = {Idiap},
       abstract = {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. By contrast, with
just a single parameter, VTLN captures very few speaker specific
characteristics when compared to the available linear transform
based adaptation techniques. This paper proposes that the merits
of VTLN can be combined with those of linear transform based
adaptation technique in a Bayesian framework, where VTLN
is used as the prior information. A novel technique of propa-
gating 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.},
            pdf = {https://publications.idiap.ch/attachments/reports/2011/Saheer_Idiap-RR-11-2012.pdf}
}