Weakly Supervised Source-Specific Sound Level Estimation in Noisy Soundscapes

Document Type

Conference Proceeding

Publication Date

1-1-2021

Abstract

While the estimation of what sound sources are, when they occur, and from where they originate has been well-studied, the estimation of how loud these sound sources are has been often overlooked. Current solutions to this task, which we refer to as source-specific sound level estimation (SSSLE), suffer from challenges due to the impracticality of acquiring realistic data and a lack of robustness to realistic recording conditions. Recently proposed weakly supervised source separation offer a means of leveraging clip-level source annotations to train source separation models, which we augment with modified loss functions to bridge the gap between source separation and SSSLE and to address the presence of background. We show that our approach improves SSSLE performance compared to baseline source separation models and provide an ablation analysis to explore our method's design choices, showing that SSSLE in practical recording and annotation scenarios is possible.

Identifier

85123451340 (Scopus)

ISBN

[9781665448703]

Publication Title

IEEE Workshop on Applications of Signal Processing to Audio and Acoustics

External Full Text Location

https://doi.org/10.1109/WASPAA52581.2021.9632767

e-ISSN

19471629

ISSN

19311168

First Page

61

Last Page

65

Volume

2021-October

Grant

1544753

Fund Ref

National Science Foundation

This document is currently not available here.

Share

COinS