True quality judging method and system for music
A quality judgment, real technology, applied in speech analysis, instruments, etc., can solve the problems of high labor and material resources, high quality of music files, huge amount of files in the music library system, etc., to avoid adverse effects.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] figure 1 It is a schematic flow chart of Embodiment 1 of the present invention, such as figure 1 As shown, a method for judging the true quality of music comprises the following steps:
[0027] S100 preprocesses the current audio signal to obtain a preprocessed audio signal;
[0028] S200 divides the preprocessed audio signal into intervals at intervals of the set fixed frequency bands, and calculates the sum of the preprocessed audio signals in each interval to form a sum sequence;
[0029] S300 Search the sum value sequence according to the set threshold, if the difference between the sum value of the preprocessed audio signal in the current interval segment and the next interval segment is greater than the first threshold value, and the current interval segment and its subsequent interval segment The sum values of the preprocessed audio signals in the interior are all less than the second threshold; then the cut-off frequency is calculated according to the curren...
Embodiment 2
[0042] Please refer to Figure 1 to Figure 2 , with reference to Embodiment 1, the process of preprocessing the current audio signal and obtaining the preprocessed audio signal in this embodiment includes the following steps:
[0043] S110 performs frame and window processing on the current audio signal to obtain a processed time-domain audio signal;
[0044] S120 Convert the time-domain audio signal into a frequency-domain audio signal, and perform absolute value processing on the frequency-domain audio signal to obtain a preprocessed audio signal.
[0045] Since the audio signal belongs to a short-term stationary process, it needs to be divided into frames. Each frame signal is regarded as a stationary process, and then windowed to obtain a time-domain audio signal. The window function can be selected according to actual needs. In this example The Hamming window can be selected, that is:
[0046] xw(n)=w(n)*x(n)
[0047] Wherein w(n) is a Hamming window whose length is N....
Embodiment 3
[0076] With reference to Embodiment 1 and Embodiment 2, in the present embodiment, firstly, the audio signal is subjected to frame-by-frame windowing processing to obtain the signal xw(n) after frame b is windowed, and the window function selects a Hamming window, and the length of xw(n) is N, where N is a power of 2.
[0077] Fast Fourier transform is performed on xw(n), and the absolute value is obtained to obtain the frequency domain signal XW(n), namely
[0078] XW(n)=abs(FFT(xw(n)))
[0079] Then follow as image 3 The steps shown obtain a preprocessed audio signal.
[0080] Such as image 3 As shown, the process of obtaining the preprocessed audio signal through the frequency domain audio signal processed by the absolute value includes the following steps:
[0081] S121 acquires the positive frequency frequency domain audio signal of the frequency domain audio signal after the absolute value processing;
[0082] S122 Perform variable substitution processing on the p...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com