Speech classification based on cuckoo algorithm and support vector machines

Speech classification is an important part of speech signal processing. It is significant to classify speech accurately and quickly in speech coding and speech synthesis. Because of the diversity and uncertainty of the speech signals, the traditional classification method is slow and not so accurate in the large-scale application of real speech classification. In order to improve the accuracy and precision of speech classification, a speech classification method based on support vector machine optimized by cuckoo algorithm(CS-SVM) is proposed. Firstly, choose four types of music: folk songs, Guzheng, rock and pop. And adopt the cepstral coefficient to extract speech feature, then use the support vector machine optimized by the cuckoo algorithm to train the characteristic signals, and establish the optimal classifier model, and finally classify the tested speech. The results of the simulation experiment show that the support vector machine based on the cuckoo algorithm(CS-SVM) is better than the traditional SVM and BP neural network in speech recognition.