EUVIMEDEUVIMED entdecken
Crossref

A confidence-aware contrastive deep learning network for coral reef fish sound classification

Tianze Hu, Ben Liu, Xiaolei Yu, Hui Huang

The Journal of the Acoustical Society of America · 2026

DOI: 10.1121/10.0046476 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, 2026. Verfasst von Tianze Hu und 3 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Deep-Sea Science and Intelligent Technology, Institute of Deep-sea Science and Engineering, Chinese Academy of Sciences, Sany…. Hauptthemen laut MEDLINE: Coral Reefs, Fishes, Deep Learning, Vocalization, Animal. Die Arbeit nennt 46 Literaturangaben. Gefördert von: Institute of Deep-sea Science and Engineering, Chinese Academy of Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vocalizations of coral reef fishes provide critical insights into population dynamics, community structure, and ecological processes, making passive acoustic monitoring an essential tool for coral reef conservation and management. However, automatic recognition of coral reef fish sounds remains highly challenging due to strong background noise, pronounced intra-class variability, and high inter-class similarity. To address these challenges, a contrastive reef-acoustic learning network (CoRAL-Net) is proposed for coral reef fish sound classification, in which a robust spectro-temporal feature extractor based on a convolutional neural network–multi-head self-attention (CNN-MSA) module is designed to process the time–frequency spectrograms. Furthermore, to improve triplet construction in contrastive learning, a confidence-aware sampling strategy is proposed to adaptively form triplets based on attention-derived uncertainty and embedding strength, thereby enhancing the representational capability of the CNN-MSA extractor through informative and class-balanced sample selection. This study validates CoRAL-Net on a predominantly field-collected dataset from coral reefs in Hainan Province, China, which contains three dominant types of fish sounds and natural noise recorded under challenging acoustic environments. Experimental results demonstrate that CoRAL-Net significantly outperforms the baseline methods in overall classification performance, highlighting the potential of this confidence-aware strategy to advance passive acoustic biodiversity monitoring in coral reef ecosystems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Coral ReefsFishesDeep LearningVocalization, AnimalAcousticsSignal Processing, Computer-AssistedEnvironmental MonitoringAnimalsSound SpectrographyConvolutional Neural NetworksChinaSound

Autor:innen und Institutionen

  • State Key Laboratory of Deep-Sea Science and Intelligent Technology, Institute of Deep-sea Science and Engineering, Chinese Academy of Sciences, Sanya 572000, China.
  • University of Chinese Academy of Sciences, Beijing 100049, China.
  • State Key Laboratory of Tropical Oceanography, Guangdong Provincial Key Laboratory of Applied Marine Biology, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China.
  • Sanya Joint Laboratory of Marine Science Research, Key Laboratory of Tropical Marine Biotechnology of Hainan Province, Sanya Institute of Ocean Eco-Environmental Engineering, SCSIO, Sanya 572000, China.
  • Sanya National Marine Ecosystem Research Station, Tropical Marine Biological Research Station in Hainan, Chinese Academy of Sciences, Sanya 572000, China.

Förderung

  • Institute of Deep-sea Science and Engineering, Chinese Academy of Sciences

Zitieren

APA

Hu, T., Liu, B., Yu, X., & Huang, H. (2026). A confidence-aware contrastive deep learning network for coral reef fish sound classification. The Journal of the Acoustical Society of America. https://doi.org/10.1121/10.0046476

Vancouver

Hu T, Liu B, Yu X, Huang H. A confidence-aware contrastive deep learning network for coral reef fish sound classification. The Journal of the Acoustical Society of America. 2026. doi:10.1121/10.0046476

BibTeX
@article{Hu2026,
  author = {Hu, Tianze and Liu, Ben and Yu, Xiaolei and Huang, Hui},
  title = {A confidence-aware contrastive deep learning network for coral reef fish sound classification},
  journal = {The Journal of the Acoustical Society of America},
  year = {2026},
  doi = {10.1121/10.0046476}
}
Kostenlos starten →