arXiv Machine Learning July 27, 2026 By V\'ictor Rinc\'on Yepes

Phylogenetic signal in marine mammal and bird vocalizations captured by audio foundation models: the limited benefit of domain-specific pretraining

Read the original on arXiv Machine Learning →

arXiv:2607. 22458v1 Announce Type: new Abstract: Do learned audio embeddings encode structure that nobody told them to encode?

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 15

Beyond task performance: Decoding bioacoustic embeddings with speech features

arXiv:2606. 14662v1 Announce Type: new Abstract: Pretrained audio embeddings are standard in bioacoustics, yet little is known about which acoustic features these models encode, nor which are useful for a given task.

By Ines Nolasco, Jules Cauzinille, Marius Miron, Gagan Narula, Milad Alizadeh, Emmanuel Fernandez, Matthieu Geist, Ellen Gilsenan-McMahon, Olivier Pietquin, Emmanuel Chemla, Sara Keen

rag

arXiv AI

Sep 16

Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal repertoires using frozen audio encoders

arXiv:2609.16612v1 Announce Type: cross Abstract: Vocal repertoires can differ in acoustic-event type accumulation and temporal organization, yet direct comparison is difficult because corpora use di...

By Mudit Sinha, Sanika Chavan

arXiv Machine Learning

Sep 15

MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training

arXiv:2609.15221v1 Announce Type: cross Abstract: Passive acoustic monitoring can measure biodiversity at larger scales, but time--frequency annotation of animal vocalizations is expensive, site-spec...

By Tianyi Xu, Daniel Pimentel-Alarc\'on, Zuzana Bu\v{r}ivalov\'a, Claudia Sol\'is-Lemus

arXiv Machine Learning

Jul 16

MetaPerch: Learning from metadata for bioacoustics foundation models

arXiv:2607. 14072v1 Announce Type: new Abstract: Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data.

By Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer

benchmarks

Hugging Face Trending Papers

Jul 15

MetaPerch: Learning from metadata for bioacoustics foundation models

Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutilized potential in the form of recording metadata readily available within these community-driven data hubs.

benchmarks

arXiv Machine Learning

Jul 7

Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types

arXiv:2607. 03304v1 Announce Type: cross Abstract: Reliable analysis of bird vocalisations in passive acoustic monitoring requires models handling multiple, imbalanced annotation targets.

By Paria Vali Zadeh, Sven Tomforde

fine-tuning

One email a morning, machine-written

Related stories

Beyond task performance: Decoding bioacoustic embeddings with speech features

Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal repertoires using frozen audio encoders

MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training

MetaPerch: Learning from metadata for bioacoustics foundation models

MetaPerch: Learning from metadata for bioacoustics foundation models

Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types