Brazilian Vowels Recognition using a New Hierarchical Decision Structure with Wavelet Packet and SVM
Adriano de Andrade Bresolin, Adrião Duarte Dória Neto, Pablo Javier Alsina · 2007
In this work, a new phoneme recognition system is proposed. The base of decision of the proposed system is the tongue position and roundedness of the lips. The features of the speech are the coefficients of wavelet packet transform with sub-bands selected through the Mel scale. The SVM (support vector machine) is used as classifier in the structure of a hierarchical committee machine. The database used for the recognition was a set of oral vocalic phonemes of the Portuguese language. The experimental results show success rates of 98.07% for the user-dependent case and 91.01% for the user-independent case. This new proposal increased 4.1% and 3.5% the success rate in relation to the "one vs. all" decision strategy, to user-dependent and user-independent case respectively.