Joint Analysis of Acoustic Events and Scenes Based on Multitask Learning

TL;DR

This paper introduces a multitask learning approach that jointly analyzes acoustic events and scenes, leveraging their relationship to improve detection performance in environmental sound analysis.

Contribution

It proposes a novel multitask neural network model that shares information between event detection and scene classification tasks, enhancing accuracy.

Findings

Improved acoustic event detection by 10.66 percentage points in F-score.

Demonstrated effectiveness on TUT Sound Events and Acoustic Scenes datasets.

Showed that joint analysis benefits from shared information between tasks.

Abstract

Acoustic event detection and scene classification are major research tasks in environmental sound analysis, and many methods based on neural networks have been proposed. Conventional methods have addressed these tasks separately; however, acoustic events and scenes are closely related to each other. For example, in the acoustic scene `office', the acoustic events `mouse clicking' and `keyboard typing' are likely to occur. In this paper, we propose multitask learning for joint analysis of acoustic events and scenes, which shares the parts of the networks holding information on acoustic events and scenes in common. By integrating the two networks, we expect that information on acoustic scenes will improve the performance of acoustic event detection. Experimental results obtained using TUT Sound Events 2016/2017 and TUT Acoustic Scenes 2016 datasets indicate that the proposed method improves the performance of acoustic event detection by 10.66 percentage points in terms of the F-score, compared with a conventional method based on a convolutional recurrent neural network.