Support vector machine based classification method of base-band time-domain voice-frequency signal

Abstract

The invention relates to a support vector machine based classification method of base-band time-domain voice-frequency signals, comprising the following steps of: firstly segmenting a base-band time-domain voice-frequency signal sequence to obtain initial segmented subsequences; then respectively subtracting respective mean value from each initial segmented subsequence to obtain zero-mean-value segmented subsequences; then carrying out windowing treatment on each zero-mean-value segmented subsequence, respectively carrying out Fourier transformation treatment on results to obtain the spectrum amplitudes of the zero-mean-value segmented subsequences, and respectively solving the standard difference of each spectrum amplitude to obtain a characteristic quantity; sequentially combining the zero-mean-value segmented subsequences into a long subsequence according to an order; then calculating a normalized autocorrelation matrix of the long subsequence, and carrying out singular value decomposition on the normalized autocorrelation matrix to obtain a demarcation point of a subspace; then calculating the signal to noise ratio parameter of an other characteristic quantity; and finally sending an input vector composed of the two characteristic quantities into a trained SVM (Support Vector Machine) classifier to identify the classification of base-band time-domain voice-frequency signals and distinguish a voice signal and a noise signal.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and in particular relates to a baseband time-domain audio signal classification method based on a support vector machine. Background technique [0002] The present invention is applied in a radio detection system. The processed signal is a demodulated baseband time-domain audio signal. The signal may be a speech signal polluted by noise to varying degrees, or a pure noise signal. The noise is represented by white The noise is dominant and mixed with a small amount of colored noise. A classifier is constructed by using the principle of SVM to identify and classify the signal types simply and effectively. [0003] The following articles and patent documents basically cover the main background technologies in this field. In order to explain the development process of the technology, let them be arranged in chronological order, and introduce the main contributions of the literature one by ...

AI Technical Summary

Problems solved by technology

[0011] The principle and method of signal SNR estimation based on SVD are proposed, which is simple and easy to implement. The performance of this method is not discussed, and the selection method of calculation parameters is not given.

Images