A method and system for identifying the degree of confusion in a sound signal

Abstract

The invention discloses a method and system for identifying the mixing degree of a sound signal, comprising: cutting the sound signal into sound data of equal duration, preprocessing the sound data, and selecting reference data; calculating the power spectral density curve of each segment of data ;Intercept the main power spectrum interval in the power spectral density curve; calculate the correlation between the main power spectrum interval of each piece of data and the main power spectrum interval of the reference data; calculate the integral of the main power spectrum interval of each piece of data and the reference data; fuse the main power The calculation result of spectral interval integration and correlation calculates the degree of confusion of each segment of data; the identification system disclosed by the present invention includes a signal acquisition module, a first signal processing module, a second signal processing module, a sound signal confusion degree generation module, and a data Storage module, display module; the recognition method and system provided by the present invention realize the measurement of the mixed degree of signals, and make up for the deficiencies in the technical field of sound signal processing in related aspects.

Description

technical field [0001] The invention relates to the field of sound signal processing, in particular to a method and system for recognizing the mixing degree of sound signals. Background technique [0002] Accurate identification of contained sounds from sound signals is beneficial to supplement or replace other sensing systems for target identification. However, if multiple sounds are mixed in the sound signal, it is difficult for sound signal processing methods, such as machine learning and deep learning methods, to accurately identify the sounds contained in the signal, and the resulting sound recognition results are invalid . [0003] At present, there is no method to measure the degree of confusion of the sound signal. In order to determine whether the sound recognition result of the sound signal processing method is effective, there is an urgent need for a method and system for recognizing the degree of confusion of the sound signal to measure the degree of confusion o...

AI Technical Summary

Problems solved by technology

The higher the degree of confusion, the more complex the sound source of the sound signal. The sound signal with high degree of confusion cannot be identified by the sound signal processing method, because the accuracy of the obtained sound recognition results is low; the sound signal with low degree of confusion can be recognized by the sound signal processing methods to obtain accurate recognition results

Images