Sound field decomposition based on two-stage neural networks

TL;DR

This paper introduces a two-stage neural network approach for sound field decomposition and source localization, achieving higher accuracy than traditional methods through simulation-based training and regression-based localization.

Contribution

It presents a novel neural network framework that separates sound sources and localizes them as a regression task, improving accuracy over existing techniques.

Findings

Higher source-localization accuracy compared to conventional methods.

Enhanced sound-field-reconstruction accuracy.

Effective use of simulation-generated datasets for training.

Abstract

A method for sound field decomposition based on neural networks is proposed. The method comprises two stages: a sound field separation stage and a single-source localization stage. In the first stage, the sound pressure at microphones synthesized by multiple sources is separated into one excited by each sound source. In the second stage, the source location is obtained as a regression from the sound pressure at microphones consisting of a single sound source. The estimated location is not affected by discretization because the second stage is designed as a regression rather than a classification. Datasets are generated by simulation using Green's function, and the neural network is trained for each frequency. Numerical experiments reveal that, compared with conventional methods, the proposed method can achieve higher source-localization accuracy and higher sound-field-reconstruction accuracy.