%Aigaion2 BibTeX export from Idiap Publications
%Saturday 23 November 2024 05:46:25 AM

@INPROCEEDINGS{Saheer_ISCASPEECHSYNTHESISWORKSHOP(SSW7)_2010,
         author = {Saheer, Lakshmi and Dines, John and Garner, Philip N. and Liang, Hui},
       projects = {Idiap, EMIME},
          month = {9},
          title = {Implementation of VTLN for Statistical Speech Synthesis},
      booktitle = {Proceedings of ISCA Speech Synthesis Workshop},
           year = {2010},
       location = {Kyoto, Japan},
       crossref = {Saheer_Idiap-RR-32-2010},
       abstract = {Vocal tract length normalization is an important feature normalization technique that can be used to perform
speaker adaptation when very little adaptation data is available. It was shown earlier that VTLN can be applied to statistical speech synthesis and was shown to give additive improvements to CMLLR. This paper presents an EM optimization for estimating more accurate warping factors. The EM formulation helps to embed the feature normalization in the HMM training. This helps in estimating the warping factors more efficiently and enables the use of multiple (appropriate) warping factors for different state clusters of the same speaker.},
            pdf = {https://publications.idiap.ch/attachments/papers/2010/Saheer_ISCASPEECHSYNTHESISWORKSHOP(SSW7)_2010.pdf}
}



crossreferenced publications: 
@TECHREPORT{Saheer_Idiap-RR-32-2010,
         author = {Saheer, Lakshmi and Dines, John and Garner, Philip N. and Liang, Hui},
       projects = {Idiap, EMIME},
          month = {8},
          title = {Implementation of VTLN for Statistical Speech Synthesis},
           type = {Idiap-RR},
         number = {Idiap-RR-32-2010},
           year = {2010},
    institution = {Idiap},
       abstract = {Vocal tract length normalization is an important feature normalization technique that can be used to perform
speaker adaptation when very little adaptation data is available. It was shown earlier that VTLN can be applied to statistical speech synthesis and was shown to give additive improvements to CMLLR. This paper presents an EM optimization for estimating more accurate warping factors. The EM formulation helps to embed the feature normalization in the HMM training. This helps in estimating the warping factors more efficiently and enables the use of multiple (appropriate) warping factors for different state clusters of the same speaker.},
            pdf = {https://publications.idiap.ch/attachments/reports/2010/Saheer_Idiap-RR-32-2010.pdf}
}