A Rule-Based Method for Homograph Disambiguation in Brazilian Portuguese Text-to-Speech Systems

  • Denilson C. Silva
  • Daniela Braga
  • Fernando Gil V. Resende Jr.

Abstract

This work presents a rule-based algorithm set used to decide the pronunciation of homographs applied to a Brazilian Portuguese (BP) text-to-speech (TTS) system. The proposed approach is composed of a morphosyntactic analysis, which deals with homographs that belong to different part-of-speech (POS), and a semantic analysis, which deals with homographs that belong to the same POS. The algorithms were implemented to solve ambiguities for 111 homograph pairs organized into 23 disambiguation algorithms, and tested with three types of texts: news, Bible and literature. Computer experiments showed that a correct homograph pronunciation is obtained in 99.00% of the occurrences.
Published
14-06-2015
How to Cite
C. Silva, D., Braga, D., & Gil V. Resende Jr., F. (2015). A Rule-Based Method for Homograph Disambiguation in Brazilian Portuguese Text-to-Speech Systems. Journal of Communication and Information Systems, 27(1). https://doi.org/10.14209/jcis.2012.1
Section
Regular Papers