Method and device for classifying voice data

Abstract

The embodiment of the invention discloses a method and device for classifying voice data. The method for classifying the voice data comprises the steps that first voice data of the category to be recognized are obtained; windowing is carried out on the voice time shaft of the first voice data according to a preset windowing algorithm; an MFCC feature vector is extracted for the voice data in each window; vector quantization is carried out on each MFCC feature vector to obtain a one-dimensional first feature value; all the first feature values are calculated according to a preset histogram drawing algorithm to obtain a first histogram of the first voice data; similarity calculation is carried out on the first histogram and preset histogram feature templates corresponding to the voice data of various voice categories, and a first histogram feature template most similar to the first histogram is obtained; the voice category of the feature template is the voice category of the first voice data. Compared with the prior art, according to the technical scheme, the accuracy and speed of classifying the voice data are improved.

Description

technical field [0001] The invention relates to the technical field of multimedia data processing, in particular to an audio data classification method and device. Background technique [0002] With the rapid development of multimedia technology and network technology, audio data has grown exponentially. Correspondingly, a large amount of audio data information has also appeared on the Internet, which is widely used in education, entertainment, news, advertising and other fields. become an important part of people's daily life. Therefore, how to classify these audio data is an urgent problem to be solved. [0003] At present, in the prior art, feature vector extraction is first performed on audio data, and then the audio data is classified based on the GMM model. Since the dimension of the extracted feature vector is usually 39 dimensions or more, a large amount of labeled data is required to obtain the GMM model from the feature vector training under the framework of the ...

AI Technical Summary

Problems solved by technology

Since the dimension of the extracted feature vector is usually 39 dimensions or more, a large amount of labeled data is required to obtain the GMM model from the feature vector training under the framework of the GMM model, and this labeled data consumes a lot of manpower. The amount of data obtained is relatively small, which will cause the problem of data sparseness, and the accuracy of audio data classification is not high

In addition, due to the high dimension of the feature vector, the corresponding amount of calculation of the above training process is relatively large, so the training process is slow and the speed of audio data classification is low.

Images