Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Feb 10;23(4):2032.
doi: 10.3390/s23042032.

Forest Sound Classification Dataset: FSC22

Meelan Bandara  1 , Roshinie Jayasundara  1 , Isuru Ariyarathne  1 , Dulani Meedeniya  1 , Charith Perera  2
Affiliations

Forest Sound Classification Dataset: FSC22

Meelan Bandara et al. Sensors (Basel). .

Abstract

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.

Keywords: Freesound; deep learning; environment sound classification; forest acoustic dataset; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
ESC-50 dataset.
Figure 2
Figure 2
Urbansound8K dataset.
Figure 3
Figure 3
SONYC-UST-V2 dataset.
Figure 4
Figure 4
FSC22 taxonomy.
Figure 5
Figure 5
Overall procedure.
Figure 6
Figure 6
The number of audio samples per class.
Figure 7
Figure 7
The number of selected audio samples per class.
Figure 8
Figure 8
Feature preparation methodology.
Figure 9
Figure 9
The CNN based architecture of the model.
Figure 10
Figure 10
Class accuracies obtained in human classification.
Figure 11
Figure 11
Confusion matrix for XGBoost-based classification with MFCC and augmented data.
Figure 12
Figure 12
Confusion matrix for CNN-based classification with mel spectrogram and augmented data.
See this image and copyright information in PMC

References

    1. Zhang C., Zhan H., Hao Z., Gao X. Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models. Forests. 2023;14:206. doi: 10.3390/f14020206. - DOI
    1. Anđelić B., Radonjić M., Djukanović S. Sound-based logging detection using deep learning; Proceedings of the 2022 30th Telecommunications Forum (TELFOR); Belgrade, Serbia. 15–16 November 2022; pp. 1–4. - DOI
    1. Mporas I., Perikos I., Kelefouras V., Paraskevas M. Illegal Logging Detection Based on Acoustic Surveillance of Forest. Appl. Sci. 2020;10:7379. doi: 10.3390/app10207379. - DOI
    1. Andreadis A., Giambene G., Zambon R. Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices. Sensors. 2021;21:7593. doi: 10.3390/s21227593. - DOI - PMC - PubMed
    1. Segarceanu S., Olteanu E., Suciu G. Forest Monitoring Using Forest Sound Identification; Proceedings of the 2020 43rd International Conference on Telecommunications and Signal Processing (TSP); Milan, Italy. 7–9 July 2020; pp. 346–349. - DOI

LinkOut - more resources