A sound source identification method based on array expansion and SE-moving inverse bottleneck convolutional neural network

By combining EAG-U-Net and SE-MBCNet networks, the problem of insufficient accuracy and robustness of traditional sound source localization methods in complex environments is solved, and the effect of improving the accuracy and clarity of sound source localization is achieved without increasing the physical array.

CN119767201BActive Publication Date: 2025-11-14ANHUI UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202411877044.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-12-19
Publication Date
2025-11-14
Estimated Expiration
2044-12-19

AI Technical Summary

Technical Problem

Traditional sound source localization methods suffer from reduced accuracy and robustness in complex environments with high noise levels or a limited number of arrays. Furthermore, increasing the number of sensors leads to higher hardware costs and computational burdens, making it difficult to improve localization accuracy without increasing the physical array.

Method used

A sound source identification method based on array extension and SE moving inverse bottleneck convolutional neural network is adopted. The sound source distribution map predicted by the 18-array MUSIC algorithm is converted into the sound source distribution map predicted by the 64-array MUSIC algorithm through the EAG-U-Net data conversion model. The image processing is combined with the SE-MBCNet network to improve the localization accuracy and robustness.

Benefits of technology

It significantly improves the accuracy and robustness of sound source localization, reduces the number of microphone arrays required, enhances its application capabilities in complex acoustic environments, and improves the clarity and accuracy of sound source distribution maps.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention relates to a sound source identification method based on array expansion and SE (Search Engine Attention) mobile inverse bottleneck convolutional neural network, comprising: acquiring an 18-array sound source distribution map calculated using the MUSIC algorithm based on the sound pressure cross-spectrum matrix; inputting the 18-array sound source distribution map into an EAG-U-Net data conversion model to convert the 18-array sound source distribution map into a 64-array sound source distribution map, achieving the effect of expanding the microphone array. This model introduces the EAG mechanism to optimize model feature selection in the spatial and channel dimensions, improving the model's representational ability and accuracy in the data conversion process, and generating an acoustic imaging map after data conversion; inputting the 64-array sound source distribution map into a mobile inverse bottleneck convolutional neural network model based on the SE attention mechanism for feature extraction and image reconstruction to obtain a predicted sound source distribution map; and performing local maxima detection using the predicted sound source distribution map to obtain sound source localization and intensity.
Need to check novelty before this filing date? Find Prior Art