Acoustic models comparison using HTK and the Spoltech corpus to Brazilian Portuguese

  • Authors:

  • Yuri T. Passos;Carlos A. F. Pimentel Filho;Uriel Marx C. Bispo;Leonardo Nogueira Matos

  • Affiliations:

  • IADe -- Instituto Atalaia de Pesquisa e Desenvolvimento, Bairro Capucho, Aracaju - Sergipe - Brasil;IADe -- Instituto Atalaia de Pesquisa e Desenvolvimento, Bairro Capucho, Aracaju - Sergipe - Brasil;IADe -- Instituto Atalaia de Pesquisa e Desenvolvimento, Bairro Capucho, Aracaju - Sergipe - Brasil;UFS -- Universidade Federal de Sergipe, São Cristóvão - Sergipe - Brasil

  • Venue:
  • WebMedia '09 Proceedings of the XV Brazilian Symposium on Multimedia and the Web
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper shows a comparison between Hidden Markov Models (HMM) trained with 12 mel-cepstral coefficients plus extra(s) parameter(s) and two different HMM initialization ways. Thus, it compares the models, in order to detect the more robust parameter added to the mel-cepstral vector in an Automatic Speech Recognizer (ASR) system for the Brazilian Portuguese. To perform such experiments, it uses the HTK to train the HMMs. All the HMMs models used the same speech training base, which is the Spoltech corpus.