5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

A Model of Segment (and Pause) Duration Generation for Brazilian Portuguese Text-To-Speech Synthesis

Plinio A. Barbosa

Laboratorio de Fonetica Acústica e Psicolinguistica Experimental-LAFAPE, Instituto de Estudos da Linguagem Universidade Estadual de Campinas, Brazil

This work presents and evaluates a model of segmental duration generation for Brazilian Portuguese where the notion of macrorhythmic unit is the starting point to drastically simplify duration assignment and to allow pause insertion as an integrated procedure of generation. This model is preferred to random assignment with the same error distribution. Some aspects of rhythm phonetics and phonology are also discussed that constitute a first step to the understanding of the prosodic component of the language under study.

Full Paper
Acoustic Examples   #1   #2   #3  

Bibliographic reference.  Barbosa, Plinio A. (1997): "A model of segment (and pause) duration generation for Brazilian Portuguese text-to-speech synthesis", In EUROSPEECH-1997, 2655-2658.