ISCA Archive Eurospeech 1991
ISCA Archive Eurospeech 1991

DIXI - portuguese text-to-speech system

Luis C. Oliveira, M. Ceu Viana, Isabel M. Trancoso

This paper describes the software architecture of the Portuguese text-to-speech system DIXI1. The system has three major modules. The first one contains the text normalizer and searches each word in the lexicon. The second one is a multi-level rule based module for lexical stress assignment, orthographic to phonetic transcription, metrically based prosodic patterning and for generating the evolution of the synthesizer parameters. The final module is the Klatt 80 formant synthesizer. The paper describes each of these main modules, emphasizing the particularities of text-to-speech synthesis in the Portuguese language. Keywords: Speech Synthesis; Text-to-speech Systems; Portuguese Language; Synthesis-by-rule.

doi: 10.21437/Eurospeech.1991-284

Cite as: Oliveira, L.C., Viana, M.C., Trancoso, I.M. (1991) DIXI - portuguese text-to-speech system. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 1239-1242, doi: 10.21437/Eurospeech.1991-284

  author={Luis C. Oliveira and M. Ceu Viana and Isabel M. Trancoso},
  title={{DIXI - portuguese text-to-speech system}},
  booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},