Consonantal recognition using SVM and a hierarchical decision structure based in the articulatory phonetics

Authors:
Adriano de Andrade Bresolin;Hermes Irineu Del Monego
Affiliations:
UFTPR - Technological Federal University of the Paraná, Brazil, Medianeira, P.R. Brazil;UFTPR - Technological Federal University of the Paraná, Brazil, Medianeira, P.R. Brazil
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part II
Year:
2012

Citing 2
Cited 0

Phoneme recognition using wavelet based features

Information Sciences—Informatics and Computer Science: An International Journal - Special issue on recent advances in soft computing
A new hierarchical decision structure using wavelet packet and SVM for brazilian phonemes recognition

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new concept of making the Consonantal Recognition is proposed in this work, where used units (phonemes and syllables) to make the word recognition. This concept was carried out by a hierarchical decision structure, based on the Articulatory Phonetics and SVM. The speech features used were MFCC and WPT. Eighteen consonantal phonemes have been used in the recognition. The database used for the recognition was a set of two-syllable words of the Brazilian Portuguese language. The experimental results showed success rates of 98.41% for the user-dependent case. Our focus was the dependent speaker in order to validate the new proposal.