Multi-output sound source recognition method and vehicle-mounted multi-sound-source system based on method
A recognition method and multi-sound source technology, applied to frequency/direction characteristic devices, etc., can solve problems such as poor user experience and sound source errors, and achieve the effects of improving system utilization, avoiding errors, and improving user experience
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0042] Example one:
[0043] Make a linear regression judgment on the difference between the first sound data and the second sound data, such as image 3 As shown, including the following steps:
[0044] S211. Obtain the difference between the first sound data and the second sound data frame by frame, and obtain a total of n Difference
[0045] S212. Set frame to abscissa x , Set the first i frame xi , The difference between the first sound data and the second sound data is the ordinate y , The first i The difference corresponding to the frame is yi , According to this n The set of data is fitted to a straight line, and according to the actual situation, it is simplified to a one-variable linear regression, which is a straight line equation y=kx+b.
[0046] S213. Calculate the slope of the one-variable linear regression equation , Is the average of the abscissa, It is the average value of the ordinate, and the slope is used as the comparison value.
[0047] If the first sound data ou...
Example Embodiment
[0049] Embodiment two:
[0050] The judgment is made by calculating the variance characteristic values of the first sound data and the second sound data respectively, such as Figure 4 As shown, including the following steps:
[0051] S221. Responding to the first sound data in units of frames And second sound data Calculate the variance to obtain the variance of the first sound data , The variance of the second sound data
[0052] S222. Variance of the first sound data Variance with the second sound data Do subtraction
[0053] S223. Obtain the variance value, and use the variance value as the comparison value.
[0054] Normally, if the first sound data output by the original car host is the same as the second sound data output by the post-installation host, the two variances should be the same, that is, the comparison value is 0. A threshold range centered on 0 can be set within the error range. If the variance value is within the threshold range, continue to output the secon...
Example Embodiment
[0055] Embodiment three:
[0056] After normalizing the first sound data and the second sound data, the difference is made frame by frame, and the difference is judged according to the sum, such as Figure 5 As shown, including the following steps:
[0057] S231. Perform MIN-MAX normalization processing on the first sound data and the second sound data respectively: ,among them: X* Is the value after normalization; X Is the value before normalization; min Is the minimum value of this sampled data group; max It is the maximum value of this sampled data group.
[0058] S232. Obtain the normalized first sound data frame by frame And second sound data Difference of ,among them .
[0059] S233. Change the difference of each frame Add to get the difference sum , And add the difference As a comparison value.
[0060] Normally, if the first sound data output by the original car host is the same as the second sound data output by the post-installation host, the difference between them...
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.
© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap