Band Energy Based GMM Speech with Noise Classification Algorithm

Speech classification is an important research topic in the speech signal processing area. Rapidly and concisely speed classification is meaningful for speech coding and speech synthesis. For the deficiency of currently available classification features and classification algorithms, this paper proposes a novel algorithm through using the energy distribution within each frequency band in Mel-frequency scale as the classification feature and creating Gaussian mixture model and classifying the speech signal into Speech consonant, vowel and Speechless parts with the maximum a posterior classification. Simulation shows that the proposed algorithm is able to provide accurate classification result even in noisy environment.