In the present paper, a hidden-semi Markov model (HSMM) based speech synthesis system is proposed. In a hidden Markov model (HMM) based speech synthesis system which we have proposed, rhythm and tempo are controlled by state duration probability distributions modeled by single Gaussian distributions. To synthesis speech, it constructs a sentence HMM corresponding to an arbitrarily given text and determine state durations maximizing their probabilities, then a speech parameter vector sequence is generated for the given state sequence. However, there is an inconsistency: although the speech is synthesized from HMMs with explicit state duration probability distributions, HMMs are trained without them. In the present paper, we introduce an HSMM, which is an HMM with explicit state duration probability distributions, into the HMM-based speech synthesis system. Experimental results show that the use of HSMM training improves the naturalness of the synthesized speech.
Cite as: Zen, H., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T. (2004) Hidden semi-Markov model based speech synthesis. Proc. Interspeech 2004, 1393-1396, doi: 10.21437/Interspeech.2004-460
@inproceedings{zen04b_interspeech, author={Heiga Zen and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title={{Hidden semi-Markov model based speech synthesis}}, year=2004, booktitle={Proc. Interspeech 2004}, pages={1393--1396}, doi={10.21437/Interspeech.2004-460} }