ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Speech synthesis using HMM-based acoustic unit inventory

Jindrich Matousek

The usage of multiple Hidden Markov Models (HMMs) to prepare a Czech acoustic unit inventory and speech synthesis based on this inventory are presented in this paper. Triphone HMMs are trained on the basis of the speech corpus spoken by a single speaker. The states of triphone HMMs are automatically clustered down using binary decision trees. The clustered states are then used to automatically segment the speech corpus and to create a speech segment database. The acoustic unit inventory constructed in this way is assumed to enable more precise context modeling than was previously possible. Concatenation-based speech synthesizer can be designed on the basis of the speech segment database. Several speech synthesis techniques are discussed for this purpose. In the end, a Czech text-to-speech (TTS) system is presented.


doi: 10.21437/Eurospeech.1999-507

Cite as: Matousek, J. (1999) Speech synthesis using HMM-based acoustic unit inventory. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2323-2326, doi: 10.21437/Eurospeech.1999-507

@inproceedings{matousek99_eurospeech,
  author={Jindrich Matousek},
  title={{Speech synthesis using HMM-based acoustic unit inventory}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={2323--2326},
  doi={10.21437/Eurospeech.1999-507}
}