The Community for Technology Leaders
In this work, a new concept of making the Consonantal Recognition is proposed. We used several units (phonemes, diphones and syllables) to make the word recognition. This concept was carried out by a new hierarchical decision structure, based on the Articulatory Phonetics and SVM (Support Vector Machine). The speech features used were MFCC (Mel-Frequency Cepstral Coefficient) and WPT (WaveletPacket Transform). 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.
SVM- Support Vector Machine, Speech Recognition, Wavelet Packet Transform

A. D. Neto, P. J. Alsina and A. d. Bresolin, "Consonantal Recognition Using SVM and New Hierarchical Decision Structure Based in the Articulatory Phonetics," 2008 Tenth IEEE International Symposium on Multimedia(ISM), vol. 00, no. , pp. 545-550, 2008.
103 ms
(Ver 3.3 (11022016))