8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Towards the Development of a Brazilian Portuguese Text-to-Speech System Based on HMM

R. da S. Maia (1), Heiga Zen (1), Keiichi Tokuda (1), Tadashi Kitamura (1), F.G.V. Resende Jr. (2)

(1) Nagoya Institute of Technology, Japan
(2) Federal University of Rio de Janeiro, Brazil

This paper describes the development of a Brazilian Portuguese text-to-speech system which applies a technique wherein speech is directly synthesized from hidden Markov models. In order to build the synthesizer a speech database was recorded and phonetically segmented. Furthermore, contextual informations about syllables, words, phrases, and utterances were determined, as well as questions for decision tree-based context clustering algorithms. The resulting system presents a fair reproduction of the prosody even when a small database is used for training.

Full Paper

Bibliographic reference.  Maia, R. da S. / Zen, Heiga / Tokuda, Keiichi / Kitamura, Tadashi / Resende Jr., F.G.V. (2003): "Towards the development of a brazilian portuguese text-to-speech system based on HMM", In EUROSPEECH-2003, 2465-2468.