A hybrid parametric-deep learning approach for sound event localization and detection

TL;DR

This paper presents a hybrid approach combining parametric spatial audio analysis with deep learning for sound event localization and detection, achieving significantly improved localization accuracy in a competitive challenge.

Contribution

It introduces a novel hybrid method that integrates parametric and deep learning techniques, reducing localization error by 2.6 times compared to the baseline.

Findings

Localization error reduced by a factor of 2.6

Performance comparable to baseline in detection

Effective integration of parametric and deep learning methods

Abstract

This work describes and discusses an algorithm submitted to the Sound Event Localization and Detection Task of DCASE2019 Challenge. The proposed methodology relies on parametric spatial audio analysis for source localization and detection, combined with a deep learning-based monophonic event classifier. The evaluation of the proposed algorithm yields overall results comparable to the baseline system. The main highlight is a reduction of the localization error on the evaluation dataset by a factor of 2.6, compared with the baseline performance.