T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura. Proceedings of the 7th European Conference on Speech Communication and Technology (EUROSPEECH/INTERSPEECH), page 2263-2266. Aalborg, Denmark, (September 2001)
Abstract
This paper describes improvements on the excitation model of an HMM-based text-to-speech system. In our previous work, natural spectral and pitch parameters have been generated from HMM by using a speech parameter generation algorithm. However, synthesized speech has a typical quality of ``vocoded speech'' since the system used a traditional excitation model with either a periodic impulse train or white noise. In this paper, in order to reduce the synthetic quality, a mixed excitation model used in MELP is incorporated into the system. Excitation parameters used in mixed excitation are modeled by HMMs, and generated from HMMs by a parameter generation algorithm in the synthesis phase. The result of a listening test shows that the mixed excitation model significantly improves quality of synthesized speech as compared with the traditional excitation model.
%0 Conference Paper
%1 Yoshimura2001
%A Yoshimura, Takayoshi
%A Tokuda, Keiichi
%A Masuko, Takashi
%A Kobayashi, Takao
%A Kitamura, Tadashi
%B Proceedings of the 7th European Conference on Speech Communication and Technology (EUROSPEECH/INTERSPEECH)
%C Aalborg, Denmark
%D 2001
%K imported
%P 2263-2266
%T Mixed Excitation for HMM-based Speech Synthesis
%U http://www.isca-speech.org/archive/eurospeech_2001/e01_2263.html
%X This paper describes improvements on the excitation model of an HMM-based text-to-speech system. In our previous work, natural spectral and pitch parameters have been generated from HMM by using a speech parameter generation algorithm. However, synthesized speech has a typical quality of ``vocoded speech'' since the system used a traditional excitation model with either a periodic impulse train or white noise. In this paper, in order to reduce the synthetic quality, a mixed excitation model used in MELP is incorporated into the system. Excitation parameters used in mixed excitation are modeled by HMMs, and generated from HMMs by a parameter generation algorithm in the synthesis phase. The result of a listening test shows that the mixed excitation model significantly improves quality of synthesized speech as compared with the traditional excitation model.
@inproceedings{Yoshimura2001,
abstract = {This paper describes improvements on the excitation model of an HMM-based text-to-speech system. In our previous work, natural spectral and pitch parameters have been generated from HMM by using a speech parameter generation algorithm. However, synthesized speech has a typical quality of ``vocoded speech'' since the system used a traditional excitation model with either a periodic impulse train or white noise. In this paper, in order to reduce the synthetic quality, a mixed excitation model used in MELP is incorporated into the system. Excitation parameters used in mixed excitation are modeled by HMMs, and generated from HMMs by a parameter generation algorithm in the synthesis phase. The result of a listening test shows that the mixed excitation model significantly improves quality of synthesized speech as compared with the traditional excitation model.},
added-at = {2021-02-01T10:51:23.000+0100},
address = {Aalborg, Denmark},
author = {Yoshimura, Takayoshi and Tokuda, Keiichi and Masuko, Takashi and Kobayashi, Takao and Kitamura, Tadashi},
biburl = {https://www.bibsonomy.org/bibtex/2ac9112b1ca9b3e395ce53c6bf503ebf9/m-toman},
booktitle = {Proceedings of the 7th European Conference on Speech Communication and Technology (EUROSPEECH/INTERSPEECH)},
file = {:pdfs/yoshimura_interspeech_2001.pdf:PDF},
interhash = {4efaffad45f10bb615054412f1c4e560},
intrahash = {ac9112b1ca9b3e395ce53c6bf503ebf9},
keywords = {imported},
month = sep,
owner = {schabus},
pages = {2263-2266},
timestamp = {2021-02-01T10:51:23.000+0100},
title = {Mixed Excitation for HMM-based Speech Synthesis},
url = {http://www.isca-speech.org/archive/eurospeech_2001/e01_2263.html},
year = 2001
}