A weakly supervised learning method based on optimal transport for sound sources reconstruction in the strong interference environment

Mingsheng Lyu, Liang Yu, Ran Wang, Yong Fang, Zhichao Sheng

Research output: Contribution to journalArticlepeer-review

Abstract

Reconstruction of sound sources in the strong interference environment is difficult due to the low signal-to-noise ratio of muti-channel signals recorded by the microphone array. In this research, a loss function based on optimal transport is derived to suppress background interference for sound source reconstruction. The approximated distribution of uncontaminated data is obtained by training the snapshot matrix through weakly supervised learning, which means there is no need to collect paired data. The quantitative reconstruction of the actual amplitude of the sound source is realized by a normalization strategy with the inverse tangent function. In the numerical simulation and experiment, the proposed method is able to accurately reconstruct the sound pressure level of target sound sources in the strong interference environment.

Original languageEnglish
Article number104935
JournalDigital Signal Processing: A Review Journal
Volume158
DOIs
StatePublished - Mar 2025

Keywords

  • Acoustic array measurement
  • Interference environment
  • Optimal transport
  • Sound source reconstruction
  • Weakly supervised learning

Fingerprint

Dive into the research topics of 'A weakly supervised learning method based on optimal transport for sound sources reconstruction in the strong interference environment'. Together they form a unique fingerprint.

Cite this