Adaptive Multi-scale Detection of Acoustic Events

TL;DR

This paper introduces AdaMD, an adaptive multi-scale neural network approach for acoustic event detection that leverages time-frequency analysis and multi-resolution predictions to improve accuracy and noise robustness in complex environments.

Contribution

The paper proposes a novel adaptive multi-scale detection method using hourglass and GRU modules, with an adaptive training algorithm to enhance acoustic event detection performance.

Findings

Outperforms state-of-the-art in ER and F1-score on DCASE datasets

Demonstrates noise resistance in factory environments

Effective multi-scale prediction improves detection accuracy

Abstract

The goal of acoustic (or sound) events detection (AED or SED) is to predict the temporal position of target events in given audio segments. This task plays a significant role in safety monitoring, acoustic early warning and other scenarios. However, the deficiency of data and diversity of acoustic event sources make the AED task a tough issue, especially for prevalent data-driven methods. In this paper, we start by analyzing acoustic events according to their time-frequency domain properties, showing that different acoustic events have different time-frequency scale characteristics. Inspired by the analysis, we propose an adaptive multi-scale detection (AdaMD) method. By taking advantage of the hourglass neural network and gated recurrent unit (GRU) module, our AdaMD produces multiple predictions at different temporal and frequency resolutions. An adaptive training algorithm is subsequently adopted to combine multi-scale predictions to enhance its overall capability. Experimental results on Detection and Classification of Acoustic Scenes and Events 2017 (DCASE 2017) Task 2, DCASE 2016 Task 3 and DCASE 2017 Task 3 demonstrate that the AdaMD outperforms published state-of-the-art competitors in terms of the metrics of event error rate (ER) and F1-score. The verification experiment on our collected factory mechanical dataset also proves the noise-resistant capability of the AdaMD, providing the possibility for it to be deployed in the complex environment.