%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:38:55 AM

@INPROCEEDINGS{Dines_INTERSPEECH_2009,
         author = {Dines, John and Yamagishi, Junichi and King, Simon},
       keywords = {speech recognition, speech synthesis, unified models},
       projects = {EMIME},
          month = {9},
          title = {Measuring the gap between HMM-based ASR and TTS},
      booktitle = {Proceedings of Interspeech},
           year = {2009},
       location = {Brighton, U.K.},
       crossref = {Dines_Idiap-RR-16-2009},
       abstract = {The EMIME European project is conducting research in the development
of technologies for mobile, personalised speech-tospeech
translation systems. The hidden Markov model is being
used as the underlying technology in both automatic speech
recognition (ASR) and text-to-speech synthesis (TTS) components,
thus, the investigation of unified statistical modelling approaches
has become an implicit goal of our research. As one
of the first steps towards this goal, we have been investigating
commonalities and differences between HMM-based ASR and
TTS. In this paper we present results and analysis of a series of
experiments that have been conducted on English ASR and TTS
systems measuring their performance with respect to phone set
and lexicon, acoustic feature type and dimensionality andHMM
topology. Our results show that, although the fundamental statistical
model may be essentially the same, optimal ASR and
TTS performance often demands diametrically opposed system
designs. This represents a major challenge to be addressed in
the investigation of such unified modelling approaches.},
            pdf = {https://publications.idiap.ch/attachments/papers/2009/Dines_INTERSPEECH_2009.pdf}
}



crossreferenced publications: 
@TECHREPORT{Dines_Idiap-RR-16-2009,
         author = {Dines, John and Yamagishi, Junichi and King, Simon},
       projects = {EMIME},
          month = {7},
          title = {Measuring the gap between HMM-based ASR and TTS},
           type = {Idiap-RR},
         number = {Idiap-RR-16-2009},
           year = {2009},
    institution = {Idiap},
       abstract = {The EMIME European project is conducting research in the development
of technologies for mobile, personalised speech-tospeech
translation systems. The hidden Markov model is being
used as the underlying technology in both automatic speech
recognition (ASR) and text-to-speech synthesis (TTS) components,
thus, the investigation of unified statistical modelling approaches
has become an implicit goal of our research. As one
of the first steps towards this goal, we have been investigating
commonalities and differences between HMM-based ASR and
TTS. In this paper we present results and analysis of a series of
experiments that have been conducted on English ASR and TTS
systems measuring their performance with respect to phone set
and lexicon, acoustic feature type and dimensionality andHMM
topology. Our results show that, although the fundamental statistical
model may be essentially the same, optimal ASR and
TTS performance often demands diametrically opposed system
designs. This represents a major challenge to be addressed in
the investigation of such unified modelling approaches.},
            pdf = {https://publications.idiap.ch/attachments/reports/2009/Dines_Idiap-RR-16-2009.pdf}
}