%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 12:03:43 PM

@TECHREPORT{Saheer_Idiap-RR-41-2009,
         author = {Saheer, Lakshmi and Garner, Philip N. and Dines, John and Liang, Hui},
       projects = {Idiap, EMIME},
          month = {12},
          title = {VTLN Adaptation for Statistical Speech Synthesis},
           type = {Idiap-RR},
         number = {Idiap-RR-41-2009},
           year = {2009},
    institution = {Idiap},
       crossref = {Saheer_ICASSP_2010},
       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.},
            pdf = {https://publications.idiap.ch/attachments/reports/2010/Saheer_Idiap-RR-41-2009.pdf}
}



crossreferenced publications: 
@INPROCEEDINGS{Saheer_ICASSP_2010,
         author = {Saheer, Lakshmi and Garner, Philip N. and Dines, John and Liang, Hui},
       projects = {Idiap, EMIME},
          title = {VTLN Adaptation for Statistical Speech Synthesis},
      booktitle = {Proceedings of ICASSP},
           year = {2010},
       location = {Dallas, Texas},
       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.},
            pdf = {https://publications.idiap.ch/attachments/papers/2010/Saheer_ICASSP_2010.pdf}
}