An improved sound source separation method of DPRNN

By using an improved DPRNN sound source separation method to directly process sound signals in the time domain and utilizing Bi-LSTM, ECA, and EMA modules, the limitations of time-frequency resolution and phase processing in traditional methods are overcome, achieving more efficient sound signal separation and fault diagnosis.

CN120412624BActive Publication Date: 2026-06-23HAINACORD (HUBEI) TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202510611856.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-05-13
Publication Date
2026-06-23
Estimated Expiration
2045-05-13

AI Technical Summary

Technical Problem

Traditional acoustic signal separation methods have limitations in time-frequency resolution and phase processing, resulting in low acoustic signal separation accuracy and difficulty in effectively processing complex industrial equipment acoustic signals.

Method used

An improved DPRNN sound source separation method is adopted. By constructing an encoder, separation layer and decoder, the sound signal is directly processed in the time domain using Bi-LSTM, ECA and EMA modules, which reduces the dependence on STFT and enhances the robustness and separation accuracy of the model.

Benefits of technology

It improves the accuracy and robustness of acoustic signal separation, can better capture long-term dependent information, reduces the loss of timing information, is suitable for complex acoustic signal separation tasks in industrial equipment, and improves the accuracy of fault diagnosis.

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

Abstract

The application relates to the field of acoustic signal separation, in particular to an improved DPRNN sound source separation method, which comprises the following steps: acquiring an original mixed signal; constructing an improved DPRNN acoustic signal separation model, wherein the model comprises an encoder, a separation layer and a decoder; processing the original mixed signal by using the encoder to obtain coding features; performing signal separation by using the separation layer according to the coding features, so as to extract independent source signal features from the mixed signal; and finally, restoring the source signal features by using the decoder to output separated acoustic signals. The application realizes the separation of complex acoustic signals, can be well applied to a speech separation task, can provide clear signal data for a fault diagnosis task, and enhances diagnosis accuracy.
Need to check novelty before this filing date? Find Prior Art