Audio frequency classification method

Abstract

The present invention discloses an audio classifying method, which comprises preprocessing an input audio signal and then calculating the linear predictive coding coefficient of the processed audio signal; getting the spectral envelope of the signal according to the linear predictive coding coefficient and then determining the amplitude difference value of the coefficient by an index spectrum obtained by calculation; setting a threshold according to the statistical results of the amplitude difference values and then classifying the audio signal according to the threshold. The present invention can significantly reduce calculation amount brought by the classification of audio signals and, at the same time, have high accuracy in audio signal classification. In addition, when being applied to signal processing flow in extended bandwidth self-adaptive multi-rate coding standards, the present invention can reduce the calculation amount of audio signal classification to extremely low and, in addition, can ensure that the signal processing flow codes directly using corresponding coding modes without the need of pre-coding procedures, thereby improving the coding efficiency.

Description

technical field [0001] The invention relates to the field of information processing, in particular to an audio classification method. Background technique [0002] In the Extended Adaptive Multi-Ratc-Wideband (AMR-WB+, Extended Adaptive Multi-Ratc-Wideband) coding standard, there are two core coding modes, Algebraic Code Excited Linear Prediction (ACELP, Algebraic Code Excited Linear Prediction) and Transmission Transform Coding Excitation (TCX, Transform Coded Excitation) mode, ACELP mode is more suitable for voice signals, and TCX mode is better for encoding music signals. In the AMR-WB+ standard, it is necessary to pre-encode each frame of signal, and then choose which best mode to use for encoding, but each frame of signal must be pre-encoded, which will lead to a very large amount of calculation, so it is necessary to Signals are pre-classified to reduce computation. Speech and music are the two most important types of data in audio signals, so distinguishing speech a...

AI Technical Summary

Problems solved by technology

[0005] In prior art 1, each step needs to judge the category of audio according to one or several audio features and their thresholds. Therefore, this prior art requires a relatively large amount of computation when extracting feature parameters with better performance. For example, extracting MFCC The parameters need to perform Mel filtering, discrete cosine transform (DCT, Discrete CosineTransform), etc., so the amount of calculation is increased, and the existing technology is also affected by the judgment order of multiple characteristic parameters

In addition, in prior art 2, the classifier needs to be trained with a large amount of data in advance, the whole process requires a large amount of calculation, and it is not easy to realize by hardware

Therefore, the defect of the prior art is that the amount of calculation is relatively large in the process of audio signal classification

Images