Comparação de modelos acústicos usando HTK e o corpus Spoltech para o português brasileiro

Passos, Yuri T. and Pimentel Filho, Carlos A. F. and Bispo, Uriel Marx C. and Matos, Leonardo Nogueira (2009) Comparação de modelos acústicos usando HTK e o corpus Spoltech para o português brasileiro. In: Proceedings of the XV Brazilian Symposium on Multimedia and the Web :. WebMedia ’09 . Association for Computing Machinery (ACM), New York, NY, USA, pp. 1-4. ISBN 9781605588803

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.