%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:31:21 AM

@INPROCEEDINGS{vepa_icslp04_p,
         author = {Vepa, Jithendra and King, Simon},
       projects = {Idiap},
          title = {Subjective Evaluation of Join Cost Functions Used in Unit Selection Speech Synthesis},
      booktitle = {Proceedings of ICSLP},
           year = {2004},
        address = {South Korea},
           note = {IDIAP-RR 04-26},
       crossref = {vepa_icslp04},
       abstract = {In our previous papers, we have proposed join cost functions derived from spectral distances, which have good correlations with perceptual scores obtained for a range of concatenation discontinuities. To further validate their ability to predict concatenation discontinuities, we have chosen the best three spectral distances and evaluated them subjectively in a listening test. The unit sequences for synthesis stimuli are obtained from a state-of-the-art unit selection text-to-speech system: rVoice from Rhetorical Systems Ltd. In this paper, we report listeners' preferences for each of the three join cost functions.},
            pdf = {https://publications.idiap.ch/attachments/reports/2004/rr04-26.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2004/rr04-26.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{vepa_icslp04,
         author = {Vepa, Jithendra and King, Simon},
       projects = {Idiap},
          title = {Subjective Evaluation of Join Cost Functions Used in Unit Selection Speech Synthesis},
           type = {Idiap-RR},
         number = {Idiap-RR-26-2004},
           year = {2004},
    institution = {IDIAP},
       abstract = {In our previous papers, we have proposed join cost functions derived from spectral distances, which have good correlations with perceptual scores obtained for a range of concatenation discontinuities. To further validate their ability to predict concatenation discontinuities, we have chosen the best three spectral distances and evaluated them subjectively in a listening test. The unit sequences for synthesis stimuli are obtained from a state-of-the-art unit selection text-to-speech system: rVoice from Rhetorical Systems Ltd. In this paper, we report listeners' preferences for each of the three join cost functions.},
            pdf = {https://publications.idiap.ch/attachments/reports/2004/rr04-26.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2004/rr04-26.ps.gz},
ipdmembership={speech},
}