Using Support Vector Machines and two dimensional discrete cosine transform in speech automatic recognition

This paper proposes the implementation of a Support Vector Machines (SVM) for automatic recognition of numerical speech commands. Besides the pre-processing of the speech signal with Mel Frequency Ceptral Coefficients (MFCC), is used to Discrete Cosine Transform (DCT) to generate a two-dimensional matrix used as input to SVM algorithm for generating the pattern of words to be recognized. The Support Vector Machines represent a new approach to pattern classification. SVM is used to recognize speech patterns from the mean and variance of the speech signal input through the two-dimensional array aforementioned, the algorithm trains and tests those data showing the best response. Finally shows the experimental results in speech recognition applied to Brazilian Portuguese language process.