Implementação de um Algoritmo de Divisão Silábica para Arquivos de Fala na Lígua Portuguesa
Implementation of an Automatic Algorithm for syllabic division in Portuguese Language
A new algorithm for automatic syllabic splitting in the Portuguese language is proposed, which is based on the
envelope of the speech signal of an audio file. A computational implementation in Matlab is presented and made available at
( here). Due to its straightforwardness, the proposed method is attractive for embedded systems (e.g. i-pods).
It can also be used as a screen to assist more sophisticated methods. Voice excerpts containing more than one syllable
and identified by the same envelope are named as super-syllables and they are separated subsequently.
The results indicate which samples corresponds to the beginning and end of each detected syllable. Preliminary tests
were performed to fifty words at an identification rate circa 70% (but further improvements may be incorporated to treat particular
phonemes). This algorithm is also particularly useful in voice command systems, as a tool in the teaching of Portuguese language
or even for patients with speech pathology.