Joint Analysis of Acoustic Scenes and Sound Events Based on Multitask Learning with Dynamic Weight Adaptation

06/21/2022
by   Kayo Nada, et al.
0

Acoustic scene classification (ASC) and sound event detection (SED) are major topics in environmental sound analysis. Considering that acoustic scenes and sound events are closely related to each other, the joint analysis of acoustic scenes and sound events using multitask learning (MTL)-based neural networks was proposed in some previous works. Conventional methods train MTL-based models using a linear combination of ASC and SED loss functions with constant weights. However, the performance of conventional MTL-based methods depends strongly on the weights of the ASC and SED losses, and it is difficult to determine the appropriate balance between the constant weights of the losses of MTL of ASC and SED. In this paper, we thus propose dynamic weight adaptation methods for MTL of ASC and SED based on dynamic weight average and multi–focal loss to adjust the learning weights automatically. Evaluation experiments using parts of the TUT Acoustic Scenes 2016/2017 and TUT Sound Events 2016/2017 are conducted, and we show that the proposed methods improve the scene classification and event detection performance characteristics compared with the conventional MTL-based method. We then investigate how the learning weights of ASC and SED tasks dynamically adapt as the model training progresses.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/14/2020

Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels

Sound event detection (SED) and acoustic scene classification (ASC) are ...
research
10/16/2020

Joint Analysis of Sound Events and Acoustic Scenes Using Multitask Learning

Sound event detection (SED) and acoustic scene classification (ASC) are ...
research
04/25/2020

Sound Event Detection Utilizing Graph Laplacian Regularization with Event Co-occurrence

A limited number of types of sound event occur in an acoustic scene and ...
research
03/30/2021

Environmental sound analysis with mixup based multitask learning and cross-task fusion

Environmental sound analysis is currently getting more and more attentio...
research
02/10/2021

Sound Event Detection Based on Curriculum Learning Considering Learning Difficulty of Events

In conventional sound event detection (SED) models, two types of events,...
research
10/07/2021

Sound Event Detection Guided by Semantic Contexts of Scenes

Some studies have revealed that contexts of scenes (e.g., "home," "offic...
research
07/09/2020

Capturing scattered discriminative information using a deep architecture in acoustic scene classification

Frequently misclassified pairs of classes that share many common acousti...

Please sign up or login with your details

Forgot password? Click here to reset