A GMM/CPSO speech recognition system

This paper proposes the optimization of a GMM system for the automatic recognition of numerical commands of voice using Chaotic Particle Optimization (CPSO). In addition preprocessing the speech signal with mel-frequency cepstral coefficients, we use the discrete cosine transform (DCT) to generate a two-dimensional temporal array used as input to a GMM system to generate the pattern of the words to be recognized.