Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
PLoS computational biology
2026
|
| Subjects: | |
| Online Access: | https://pubmed.ncbi.nlm.nih.gov/41790862/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1868266076986408962 |
|---|---|
| author | Acs, Richard Ibrahim, Ali Zhuang, Hanqi Chérubin, Laurent M |
| author_facet | Acs, Richard Ibrahim, Ali Zhuang, Hanqi Chérubin, Laurent M Acs, Richard Ibrahim, Ali Zhuang, Hanqi Chérubin, Laurent M |
| collection | PubMed - marine biology |
| contents | Contrastive learning for passive acoustic monitoring: A framework for sound source discovery and cross-site comparison in marine soundscapes. Acs, Richard Ibrahim, Ali Zhuang, Hanqi Chérubin, Laurent M Acoustics Animals Clustering Algorithms Sound Computational Biology Environmental Monitoring Cluster Analysis Sound Spectrography Fishes Autoencoder Marine Biology Biodiversity Machine Learning Reproducibility of Results Signal Processing, Computer-Assisted Aquatic Organisms Passive acoustic monitoring (PAM) is a powerful tool for studying marine biodiversity, but large-scale analysis of underwater recordings is constrained by noise, overlapping signals, and limited labeled data. Here, we present a scalable, unsupervised contrastive learning framework for marine soundscapes. Using a large PAM dataset spanning multiple biogeographies, we show that the proposed approach organizes recordings into clusters with well-defined internal structure, as assessed using intrinsic clustering metrics and within-cluster similarity. The resulting clusters reveal recurring acoustic patterns that correspond to broad sound-source categories, including biological sounds such as fish calls and choruses, and anthropogenic sounds such as vessel noise, without explicitly enforcing these distinctions during training. Compared with established approaches, including cepstral features, variational autoencoders, and supervised pipelines, the proposed framework produces embeddings that support more compact and stable unsupervised clustering while preserving fine-scale acoustic variation beyond predefined species labels. By learning a shared representation across recordings from multiple sites and years, we examine the reproducibility of acoustic patterns across locations and identify both site-shared and site-specific sound signatures. Although the method is not designed to recover coarse species labels, it enables label-efficient analysis by reducing reliance on manual annotation and supporting exploratory characterization of complex marine soundscapes. Together, these results highlight multi-positive contrastive learning with a teacher network and acoustically informed augmentations as an effective strategy for scalable, discovery-driven analysis of passive acoustic monitoring data. |
| format | Artículo científico |
| id | pubmed_41790862 |
| institution | PubMed |
| language | en |
| publishDate | 2026 |
| publisher | PLoS computational biology |
| record_format | pubmed |
| spellingShingle | Contrastive learning for passive acoustic monitoring: A framework for sound source discovery and cross-site comparison in marine soundscapes. Acs, Richard Ibrahim, Ali Zhuang, Hanqi Chérubin, Laurent M Acoustics Animals Clustering Algorithms Sound Computational Biology Environmental Monitoring Cluster Analysis Sound Spectrography Fishes Autoencoder Marine Biology Biodiversity Machine Learning Reproducibility of Results Signal Processing, Computer-Assisted Aquatic Organisms Contrastive learning for passive acoustic monitoring: A framework for sound source discovery and cross-site comparison in marine soundscapes. Acs, Richard Ibrahim, Ali Zhuang, Hanqi Chérubin, Laurent M Acoustics Animals Clustering Algorithms Sound Computational Biology Environmental Monitoring Cluster Analysis Sound Spectrography Fishes Autoencoder Marine Biology Biodiversity Machine Learning Reproducibility of Results Signal Processing, Computer-Assisted Aquatic Organisms Passive acoustic monitoring (PAM) is a powerful tool for studying marine biodiversity, but large-scale analysis of underwater recordings is constrained by noise, overlapping signals, and limited labeled data. Here, we present a scalable, unsupervised contrastive learning framework for marine soundscapes. Using a large PAM dataset spanning multiple biogeographies, we show that the proposed approach organizes recordings into clusters with well-defined internal structure, as assessed using intrinsic clustering metrics and within-cluster similarity. The resulting clusters reveal recurring acoustic patterns that correspond to broad sound-source categories, including biological sounds such as fish calls and choruses, and anthropogenic sounds such as vessel noise, without explicitly enforcing these distinctions during training. Compared with established approaches, including cepstral features, variational autoencoders, and supervised pipelines, the proposed framework produces embeddings that support more compact and stable unsupervised clustering while preserving fine-scale acoustic variation beyond predefined species labels. By learning a shared representation across recordings from multiple sites and years, we examine the reproducibility of acoustic patterns across locations and identify both site-shared and site-specific sound signatures. Although the method is not designed to recover coarse species labels, it enables label-efficient analysis by reducing reliance on manual annotation and supporting exploratory characterization of complex marine soundscapes. Together, these results highlight multi-positive contrastive learning with a teacher network and acoustically informed augmentations as an effective strategy for scalable, discovery-driven analysis of passive acoustic monitoring data. |
| title | Contrastive learning for passive acoustic monitoring: A framework for sound source discovery and cross-site comparison in marine soundscapes. |
| topic | Acoustics Animals Clustering Algorithms Sound Computational Biology Environmental Monitoring Cluster Analysis Sound Spectrography Fishes Autoencoder Marine Biology Biodiversity Machine Learning Reproducibility of Results Signal Processing, Computer-Assisted Aquatic Organisms |
| url | https://pubmed.ncbi.nlm.nih.gov/41790862/ |