Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909951556845568 |
|---|---|
| author | Cauzinille, Jules Miron, Marius Pietquin, Olivier Hagiwara, Masato Marxer, Ricard Rey, Arnaud Favre, Benoit |
| author_facet | Cauzinille, Jules Miron, Marius Pietquin, Olivier Hagiwara, Masato Marxer, Ricard Rey, Arnaud Favre, Benoit |
| contents | Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored. We study the transfer learning capabilities of such models on bioacoustic detection and classification tasks. We show that models such as HuBERT, WavLM, and XEUS can generate rich latent representations of animal sounds across taxa. We analyze the models properties with linear probing on time-averaged representations. We then extend the approach to account for the effect of time-wise information with other downstream architectures. Finally, we study the implication of frequency range and noise on performance. Notably, our results are competitive with fine-tuned bioacoustic pre-trained models and show the impact of noise-robust pre-training setups. These findings highlight the potential of speech-based self-supervised learning as an efficient framework for advancing bioacoustic research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04166 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds Cauzinille, Jules Miron, Marius Pietquin, Olivier Hagiwara, Masato Marxer, Ricard Rey, Arnaud Favre, Benoit Machine Learning Artificial Intelligence Computation and Language Sound 68T07 I.5.4; I.2.6; H.5.5 Self-supervised speech models have demonstrated impressive performance in speech processing, but their effectiveness on non-speech data remains underexplored. We study the transfer learning capabilities of such models on bioacoustic detection and classification tasks. We show that models such as HuBERT, WavLM, and XEUS can generate rich latent representations of animal sounds across taxa. We analyze the models properties with linear probing on time-averaged representations. We then extend the approach to account for the effect of time-wise information with other downstream architectures. Finally, we study the implication of frequency range and noise on performance. Notably, our results are competitive with fine-tuned bioacoustic pre-trained models and show the impact of noise-robust pre-training setups. These findings highlight the potential of speech-based self-supervised learning as an efficient framework for advancing bioacoustic research. |
| title | Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds |
| topic | Machine Learning Artificial Intelligence Computation and Language Sound 68T07 I.5.4; I.2.6; H.5.5 |
| url | https://arxiv.org/abs/2509.04166 |