Publication detail

Source Separation for Sound Event Detection in domestic environments using jointly trained models

DE BENITO GORRON, D. ŽMOLÍKOVÁ, K. TORRE TOLEDANO, D.

Original Title

Source Separation for Sound Event Detection in domestic environments using jointly trained models

Type

conference paper

Language

English

Original Abstract

Sound Event Detection and Source Separation are closely related tasks: whereas the first aims to find the time boundaries of acoustic events inside a recording, the goal of the latter is to isolate each of the acoustic sources into different signals. This paper presents a Sound Event Detection system formed by two independently pretrained blocks for Source Separation and Sound Event Detection. We propose a joint-training scheme, where both blocks are trained at the same time, and a two-stage training, where each block trains while the other one is frozen. In addition, we compare the use of supervised and unsupervised pre-training for the Separation block, and two model selection strategies for Sound Event Detection. Our experiments show that the proposed methods are able to outperform the baseline systems of the DCASE 2021 Challenge Task 4.

Keywords

Sound Event Detection, Source Separation, DCASE, DESED

Authors

DE BENITO GORRON, D.; ŽMOLÍKOVÁ, K.; TORRE TOLEDANO, D.

Released

5. 9. 2022

Publisher

IEEE Signal Processing Society

Location

Bamberg

ISBN

978-1-6654-6867-1

Book

Proceedings of The 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022)

Pages from

1

Pages to

5

Pages count

5

URL

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9914755

BibTex

@inproceedings{BUT179869,
  author="Diego {de Benito Gorron} and Kateřina {Žmolíková} and Doroteo {Torre Toledano}",
  title="Source Separation for Sound Event Detection in domestic environments using jointly trained models",
  booktitle="Proceedings of The 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022)",
  year="2022",
  pages="1--5",
  publisher="IEEE Signal Processing Society",
  address="Bamberg",
  doi="10.1109/IWAENC53105.2022.9914755",
  isbn="978-1-6654-6867-1",
  url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9914755"
}

Documents

diego_de benito_IWAENC2022_source.pdf