Domain-Invariant Representation Learning of Bird Sounds
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912855081615360 |
|---|---|
| author | Moummad, Ilyass Serizel, Romain Benetos, Emmanouil Farrugia, Nicolas |
| author_facet | Moummad, Ilyass Serizel, Romain Benetos, Emmanouil Farrugia, Nicolas |
| contents | Passive acoustic monitoring (PAM) is crucial for bioacoustic research, enabling non-invasive species tracking and biodiversity monitoring. Citizen science platforms provide large annotated datasets from focal recordings, where the target species is intentionally recorded. However, PAM requires monitoring in passive soundscapes, creating a domain shift between focal and passive recordings, challenging deep learning models trained on focal recordings. To address domain generalization, we leverage supervised contrastive learning by enforcing domain invariance across same-class examples from different domains. Additionally, we propose ProtoCLR, an alternative to SupCon loss which reduces the computational complexity by comparing examples to class prototypes instead of pairwise comparisons. We conduct few-shot classification based on BIRB, a large-scale bird sound benchmark to assess pre-trained bioacoustic models. Our findings suggest that ProtoCLR is a better alternative to SupCon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08589 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain-Invariant Representation Learning of Bird Sounds Moummad, Ilyass Serizel, Romain Benetos, Emmanouil Farrugia, Nicolas Sound Audio and Speech Processing Passive acoustic monitoring (PAM) is crucial for bioacoustic research, enabling non-invasive species tracking and biodiversity monitoring. Citizen science platforms provide large annotated datasets from focal recordings, where the target species is intentionally recorded. However, PAM requires monitoring in passive soundscapes, creating a domain shift between focal and passive recordings, challenging deep learning models trained on focal recordings. To address domain generalization, we leverage supervised contrastive learning by enforcing domain invariance across same-class examples from different domains. Additionally, we propose ProtoCLR, an alternative to SupCon loss which reduces the computational complexity by comparing examples to class prototypes instead of pairwise comparisons. We conduct few-shot classification based on BIRB, a large-scale bird sound benchmark to assess pre-trained bioacoustic models. Our findings suggest that ProtoCLR is a better alternative to SupCon. |
| title | Domain-Invariant Representation Learning of Bird Sounds |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.08589 |