mlsanityData to 14 Oct 2026

Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds

arXiv 2509.04166 ↗First posted 4 Sep 2025cs.LG cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 35 of its 63 references that are in the map. First posted on arXiv 4 Sep 2025.

Builds on

35 of 63 references.

References · 35

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  5. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  6. 2017Deep Image Priorcited by 1,098
  7. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  8. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  9. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  10. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  11. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 342
  12. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 286
23 more
  1. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 260
  2. 2022Comparative layer-wise analysis of self-supervised speech modelscited by 158
  3. 2019WHAM!: Extending Speech Separation to Noisy Environmentscited by 156
  4. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  5. 2022AVES: Animal Vocalization Encoder based on Self-Supervisioncited by 53
  6. 2020Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutionscited by 50
  7. 2024Towards Robust Speech Representation Learning for Thousands of Languagescited by 50
  8. 2022BEANS: The Benchmark of Animal Soundscited by 38
  9. 2024NatureLM-audio: an Audio-Language Foundation Model for Bioacousticscited by 33
  10. 2024ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasetscited by 27
  11. 2014Acoustic Scene Classificationcited by 26
  12. 2020Probing Acoustic Representations for Phonetic Propertiescited by 26
  13. 2023Transferable Models for Bioacoustics with Human Language Supervisioncited by 21
  14. 2021HumBugDB: A Large-scale Acoustic Mosquito Datasetcited by 15
  15. 2024Uncertainty-guided Contrastive Learning for Single Source Domain Generalisationcited by 14
  16. 2023Device-Robust Acoustic Scene Classification via Impulse Response Augmentationcited by 11
  17. 2024Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challengecited by 9
  18. 2025Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processingcited by 9
  19. 2021IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Researchcited by 8
  20. 2024Description on IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shiftcited by 7
  21. 2024Exploring bat song syllable representations in self-supervised audio encoderscited by 5
  22. 2023TF-SepNet: An Efficient 1D Kernel Design in CNNs for Low-Complexity Acoustic Scene Classificationcited by 4
  23. 2024On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysiscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddingscited by 1
  2. 2026Multi-layer attentive probing improves transfer of audio representations for bioacousticscited by 1
  3. 2026Beyond task performance: Decoding bioacoustic embeddings with speech featurescited by 0
  4. 2026A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classificationcited by 0