EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Voice Analysis in Dogs with Deep Learning: Development of a Fully Automatic Voice Analysis System for Bioacoustics Studies

Mahmut Karaaslan iD, Bahaeddin Turkoglu iD, Ersin Kaya iD, Tunc Asuroglu iD

Sensors · 13.12.2024 · 24 (24) · 7978

DOI: 10.3390/s24247978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.12.2024. Verfasst von Mahmut Karaaslan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Konya Technical University, 42250 Konya, Turkey. Hauptthemen laut MEDLINE: Deep Learning, Vocalization, Animal, Neural Networks, Computer. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extracting behavioral information from animal sounds has long been a focus of research in bioacoustics, as sound-derived data are crucial for understanding animal behavior and environmental interactions. Traditional methods, which involve manual review of extensive recordings, pose significant challenges. This study proposes an automated system for detecting and classifying animal vocalizations, enhancing efficiency in behavior analysis. The system uses a preprocessing step to segment relevant sound regions from audio recordings, followed by feature extraction using Short-Time Fourier Transform (STFT), Mel-frequency cepstral coefficients (MFCCs), and linear-frequency cepstral coefficients (LFCCs). These features are input into convolutional neural network (CNN) classifiers to evaluate performance. Experimental results demonstrate the effectiveness of different CNN models and feature extraction methods, with AlexNet, DenseNet, EfficientNet, ResNet50, and ResNet152 being evaluated. The system achieves high accuracy in classifying vocal behaviors, such as barking and howling in dogs, providing a robust tool for behavioral analysis. The study highlights the importance of automated systems in bioacoustics research and suggests future improvements using deep learning-based methods for enhanced classification performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningVocalization, AnimalNeural Networks, ComputerAnimalsDogsVoiceAcousticsFourier Analysis

Stichwörter der Autor:innen

CNNaudio processingautomatic behavior analysisbioacoustics

Autor:innen und Institutionen

  • Department of Computer Engineering, Konya Technical University, 42250 Konya, Turkey.
  • Department of Artificial Intelligence and Data Engineering, Ankara University, 06830 Ankara, Turkey.
  • Faculty of Medicine and Health Technology, Tampere University, 33720 Tampere, Finland.
  • VTT Technical Research Centre of Finland, 33101 Tampere, Finland.

ORCID-Profile: Mahmut Karaaslan, Bahaeddin Turkoglu, Ersin Kaya, Tunc Asuroglu

Zitieren

APA

Karaaslan, M., Turkoglu, B., Kaya, E., & Asuroglu, T. (2024). Voice Analysis in Dogs with Deep Learning: Development of a Fully Automatic Voice Analysis System for Bioacoustics Studies. Sensors, 24(24), 7978. https://doi.org/10.3390/s24247978

Vancouver

Karaaslan M, Turkoglu B, Kaya E, Asuroglu T. Voice Analysis in Dogs with Deep Learning: Development of a Fully Automatic Voice Analysis System for Bioacoustics Studies. Sensors. 2024;24(24):7978. doi:10.3390/s24247978

BibTeX
@article{Karaaslan2024,
  author = {Karaaslan, Mahmut and Turkoglu, Bahaeddin and Kaya, Ersin and Asuroglu, Tunc},
  title = {Voice Analysis in Dogs with Deep Learning: Development of a Fully Automatic Voice Analysis System for Bioacoustics Studies},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {7978},
  doi = {10.3390/s24247978}
}
Kostenlos starten →