MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources

TL;DR

This paper introduces MIMO-DoAnet, a neural network that estimates the direction of multiple sound sources with unknown count, overcoming threshold and angle assumptions of previous methods, and demonstrating significant performance improvements.

Contribution

MIMO-DoAnet is a novel multi-channel input, multi-output neural network that predicts individual source spatial spectra, simplifying source detection and addressing limitations of prior MISO algorithms.

Findings

Achieves 18.6% relative F1 score improvement over MISO baseline in 3-source scenes.

Alleviates threshold setting issues and angle assumption limitations.

Effectively detects multiple sound sources with unknown number.

Abstract

Recent neural network based Direction of Arrival (DoA) estimation algorithms have performed well on unknown number of sound sources scenarios. These algorithms are usually achieved by mapping the multi-channel audio input to the single output (i.e. overall spatial pseudo-spectrum (SPS) of all sources), that is called MISO. However, such MISO algorithms strongly depend on empirical threshold setting and the angle assumption that the angles between the sound sources are greater than a fixed angle. To address these limitations, we propose a novel multi-channel input and multiple outputs DoA network called MIMO-DoAnet. Unlike the general MISO algorithms, MIMO-DoAnet predicts the SPS coding of each sound source with the help of the informative spatial covariance matrix. By doing so, the threshold task of detecting the number of sound sources becomes an easier task of detecting whether there is a sound source in each output, and the serious interaction between sound sources disappears during inference stage. Experimental results show that MIMO-DoAnet achieves relative 18.6% and absolute 13.3%, relative 34.4% and absolute 20.2% F1 score improvement compared with the MISO baseline system in 3, 4 sources scenes. The results also demonstrate MIMO-DoAnet alleviates the threshold setting problem and solves the angle assumption problem effectively.