Resnet-conformer network with shared weights and attention mechanism for sound event localization, detection, and distance estimation

TL;DR

This paper presents a ResNet-Conformer network with shared weights and an attention mechanism for sound event localization, detection, and distance estimation, achieving improved accuracy on the DCASE 2024 challenge.

Contribution

It introduces a novel ResNet-Conformer architecture with shared weights and attention for SELD and distance estimation, enhancing performance over previous models.

Findings

F-score of 40.2% on test set

Angular Error of 17.7 degrees

Relative Distance Error of 0.32

Abstract

This technical report outlines our approach to Task 3A of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024, focusing on Sound Event Localization and Detection (SELD). SELD provides valuable insights by estimating sound event localization and detection, aiding in various machine cognition tasks such as environmental inference, navigation, and other sound localization-related applications. This year's challenge evaluates models using either audio-only (Track A) or audiovisual (Track B) inputs on annotated recordings of real sound scenes. A notable change this year is the introduction of distance estimation, with evaluation metrics adjusted accordingly for a comprehensive assessment. Our submission is for Task A of the Challenge, which focuses on the audio-only track. Our approach utilizes log-mel spectrograms, intensity vectors, and employs multiple data augmentations. We proposed an EINV2-based [1] network architecture, achieving improved results: an F-score of 40.2%, Angular Error (DOA) of 17.7 degrees, and Relative Distance Error (RDE) of 0.32 on the test set of the Development Dataset [2 ,3].