# Dual-Branch CNN for Direction-of-Arrival and Number-of-Sources Estimation

## TL;DR

This paper introduces a new neural network model that estimates both the direction of sound sources and their number, outperforming traditional methods in challenging conditions.

## Contribution

The novel dual-branch CNN with squeeze-and-excitation blocks enables simultaneous DOA and NOS estimation.

## Key findings

- The proposed model outperforms traditional algorithms in low SNR conditions.
- It performs well with limited snapshots and closely spaced incident angles.

## Abstract

Despite numerous conventional direction-of-arrival (DOA) methods, relationships between number of sources (NOS) and DOA are often ignored, which could yield meaningful estimation information. Therefore, a dual-branch Convolutional Neutral Network (CNN) integrated with squeeze-and-excitation (SE) blocks that can perform DOA and NOS estimation simultaneously is proposed to address such limitations. Extensive simulations demonstrate the superiority of the proposed model over several traditional algorithms, especially under low signal-to-noise (SNR) conditions, limited snapshots, and in closely spaced incident angle scenarios.