Back to Search
Start Over
Task-Aware Separation for the DCASE 2020 Task 4 Sound Event Detection and Separation Challenge
- Source :
- DCASE 2020-5th Workshop on Detection and Classification of Acoustic Scenes and Events, DCASE 2020-5th Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2020, Virtual, Japan
- Publication Year :
- 2020
- Publisher :
- HAL CCSD, 2020.
-
Abstract
- International audience; Source Separation is often used as a pre-processing step in many signal-processing tasks. In this work we propose a novel approach for combined Source Separation and Sound Event Detection in which a Source Separation algorithm is used to enhance the Sound Even-Detection back-end performance. In particular, we present a permutation-invariant training scheme for optimizing the Source Separation system directly with the back-end Sound Event Detection objective without requiring joint training or fine-tuning of the two systems. We show that such an approach has significant advantages over the more standard approach of training the Source Separation system separately using only a Source Separation based objective such as Scale-Invariant Signal-To-Distortion Ratio. On the 2020 Detection and Classification of Acoustic Scenes and Events Task 4 Challenge our proposed approach is able to outperform the baseline source separation system by more than one percent in event-based macro F1 score on the development set with significantly less computational requirements.
- Subjects :
- [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]
End-to-End
Time Domain
Joint Training
[INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]
Source Separation
[INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD]
Sound Event Detection
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- DCASE 2020-5th Workshop on Detection and Classification of Acoustic Scenes and Events, DCASE 2020-5th Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2020, Virtual, Japan
- Accession number :
- edsair.dedup.wf.001..02eff6180605943ef68ac1952cbdc1f4