EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Forest Sound Classification Dataset: FSC22

Meelan Bandara iD, Roshinie Jayasundara iD, Isuru Ariyarathne iD, Dulani Meedeniya iD, Charith Perera iD

Sensors · 10.02.2023 · 23 (4) · 2032

DOI: 10.3390/s23042032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.02.2023. Verfasst von Meelan Bandara und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science & Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka. Hauptthemen laut MEDLINE: Sound, Acoustics. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council, EP/W524219/1.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The study of environmental sound classification (ESC) has become popular over the years due to the intricate nature of environmental sounds and the evolution of deep learning (DL) techniques. Forest ESC is one use case of ESC, which has been widely experimented with recently to identify illegal activities inside a forest. However, at present, there is a limitation of public datasets specific to all the possible sounds in a forest environment. Most of the existing experiments have been done using generic environment sound datasets such as ESC-50, U8K, and FSD50K. Importantly, in DL-based sound classification, the lack of quality data can cause misguided information, and the predictions obtained remain questionable. Hence, there is a requirement for a well-defined benchmark forest environment sound dataset. This paper proposes FSC22, which fills the gap of a benchmark dataset for forest environmental sound classification. It includes 2025 sound clips under 27 acoustic classes, which contain possible sounds in a forest environment. We discuss the procedure of dataset preparation and validate it through different baseline sound classification models. Additionally, it provides an analysis of the new dataset compared to other available datasets. Therefore, this dataset can be used by researchers and developers who are working on forest observatory tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoundAcousticsData AccuracyForests

Stichwörter der Autor:innen

Freesounddeep learningenvironment sound classificationforest acoustic datasetmachine learning

Autor:innen und Institutionen

  • Department of Computer Science & Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka.
  • School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK.

ORCID-Profile: Meelan Bandara, Roshinie Jayasundara, Isuru Ariyarathne, Dulani Meedeniya, Charith Perera

Förderung

  • Engineering and Physical Sciences Research Council
  • EP/W524219/1

Zitieren

APA

Bandara, M., Jayasundara, R., Ariyarathne, I., Meedeniya, D., & Perera, C. (2023). Forest Sound Classification Dataset: FSC22. Sensors, 23(4), 2032. https://doi.org/10.3390/s23042032

Vancouver

Bandara M, Jayasundara R, Ariyarathne I, Meedeniya D, Perera C. Forest Sound Classification Dataset: FSC22. Sensors. 2023;23(4):2032. doi:10.3390/s23042032

BibTeX
@article{Bandara2023,
  author = {Bandara, Meelan and Jayasundara, Roshinie and Ariyarathne, Isuru and Meedeniya, Dulani and Perera, Charith},
  title = {Forest Sound Classification Dataset: FSC22},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {4},
  pages = {2032},
  doi = {10.3390/s23042032}
}
Kostenlos starten →