Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners
by Michael Pucher, Dietmar Schabus and Junichi Yamagishi
Abstract:
In this paper we evaluate a method for generating synthetic speech at high speaking rates based on the interpolation of hidden semi-Markov models (HSMMs) trained on speech data recorded at normal and fast speaking rates. The subjective evaluation was carried out with both blind listeners, who are used to very fast speaking rates, and sighted listeners. We show that we can achieve a better intelligibility rate and higher voice quality with this method compared to standard HSMM-based duration modeling. We also evaluate duration modeling with the interpolation of all the acoustic features including not only duration but also spectral and F0 models. An analysis of the mean squared error (MSE) of standard HSMM-based duration modeling for fast speech identifies problematic linguistic contexts for duration modeling.
Reference:
Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners (Michael Pucher, Dietmar Schabus and Junichi Yamagishi), In Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2010.
Bibtex Entry:
@InProceedings{Pucher2010a,
Title = {Synthesis of fast speech with interpolation of adapted {HSMMs} and its evaluation by blind and sighted listeners},
Author = {Michael Pucher and Dietmar Schabus and Junichi Yamagishi},
Booktitle = {Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH)},
Year = {2010},
Address = {Makuhari, Japan},
Month = sep,
Pages = {2186-2189},
Abstract = {In this paper we evaluate a method for generating synthetic speech at high speaking rates based on the interpolation of hidden semi-Markov models (HSMMs) trained on speech data recorded at normal and fast speaking rates. The subjective evaluation was carried out with both blind listeners, who are used to very fast speaking rates, and sighted listeners. We show that we can achieve a better intelligibility rate and higher voice quality with this method compared to standard HSMM-based duration modeling. We also evaluate duration modeling with the interpolation of all the acoustic features including not only duration but also spectral and F0 models. An analysis of the mean squared error (MSE) of standard HSMM-based duration modeling for fast speech identifies problematic linguistic contexts for duration modeling.},
File = {/download/pucher_INTERSPEECH_2010},
Owner = {schabus},
Timestamp = {2014.05.06},
Url = {http://www.isca-speech.org/archive/interspeech_2010/i10_2186.html}
}