Imagen de Portada

Multi-layer attentive probing improves transfer of audio representations for bioacoustics

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Miron, Marius, Robinson, David, Hagiwara, Masato, Parcollet, Titouan, Cauzinille, Jules, Narula, Gagan, Alizadeh, Milad, Gilsenan-McMahon, Ellen, Keen, Sara, Chemla, Emmanuel, Hoffman, Benjamin, Cusimano, Maddie, Kim, Diane, Effenberger, Felix, Lawton, Jane K., Raskin, Aza, Pietquin, Olivier, Geist, Matthieu
Formato:	Preprint
Publicado:	2026
Materias:	Sound Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AVEX: What Matters for Animal Vocalization Encoding
por: Miron, Marius, et al.
Publicado: (2025)

Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification
por: Sarkar, Eklavya, et al.
Publicado: (2026)

NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics
por: Robinson, David, et al.
Publicado: (2024)

BAGEL: Benchmarking Animal Knowledge Expertise in Language Models
por: Shen, Jiacheng, et al.
Publicado: (2026)

Robust detection of overlapping bioacoustic sound events
por: Mahon, Louis, et al.
Publicado: (2025)

Synthetic data enables context-aware bioacoustic sound event detection
por: Hoffman, Benjamin, et al.
Publicado: (2025)

Biodenoising: Animal Vocalization Denoising without Access to Clean Data
por: Miron, Marius, et al.
Publicado: (2024)

Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds
por: Cauzinille, Jules, et al.
Publicado: (2025)

Applying machine learning to primate bioacoustics: Review and perspectives
por: Jules Cauzinille, et al.
Publicado: (2024)

Audio-to-Image Bird Species Retrieval without Audio-Image Pairs via Text Distillation
por: Moummad, Ilyass, et al.
Publicado: (2026)

Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrieval
por: Moummad, Ilyass, et al.
Publicado: (2026)

On Leakage of Code Generation Evaluation Datasets
por: Matton, Alexandre, et al.
Publicado: (2024)

Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations
por: Zaiem, Salah, et al.
Publicado: (2024)

Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation
por: Duret, Jarod, et al.
Publicado: (2024)

Review of advanced practice nurse role in infection throughout the hematopoietic stem cell transplant journey
por: Maddie Gilsenan, et al.
Publicado: (2024)

pycnet-audio: A Python package to support bioacoustics data processing
por: Ruff, Zachary J., et al.
Publicado: (2025)

Open Implementation and Study of BEST-RQ for Speech Processing
por: Whetten, Ryan, et al.
Publicado: (2024)

A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models
por: Whetten, Ryan, et al.
Publicado: (2026)

Whombat: An open‐source audio annotation tool for machine learning assisted bioacoustics
por: Santiago Martínez Balvanera, et al.
Publicado: (2024)

Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use
por: Parcollet, Titouan, et al.
Publicado: (2025)

Benchmarking Rotary Position Embeddings for Automatic Speech Recognition
por: Zhang, Shucong, et al.
Publicado: (2025)

Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition
por: Parcollet, Titouan, et al.
Publicado: (2024)

Linear-Complexity Self-Supervised Learning for Speech Processing
por: Zhang, Shucong, et al.
Publicado: (2024)

SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding
por: Parcollet, Titouan, et al.
Publicado: (2023)

Application of SINTACS method to the aquifers of Piana di Palermo, Sicily, Italy
por: G. Cusimano
Publicado: (2004)

The Violence of the Letter
por: McMahon, Melanie
Publicado: (2023)

Applying economic analysis to technical asistance projects / Gary McMahon
por: McMahon, Gary
Publicado: (1997)

Post-Oslo Peace Initiatives and the Discourse of Palestinian-Israeli Relations
por: Sean McMahon
Publicado: (2011)

Terapêutica clínica - Insulina inalada para a diabetes mellitus
por: Graham T McMahon
Publicado: (2007)

Altered States: Books into Video.
por: McMahon, Judith
Publicado: (1990)

Computerizing the Chinese International School Libraries.
por: McMahon, Marilyn
Publicado: (1993)

Feeding the Byzantine City: The Archaeology of Consumption in the Eastern Mediterranean (ca. 500–1500). Edited by JoanitaVroom. Medieval and Post‐Medieval Mediterranean Archaeology5. Turnhout: Brepols. 2023. 350 pp. + 157 figures, chiefly colour. €75. ISBN 978 2 503 60566 1. ISSN 2565 8719.
por: Lucas McMahon
Publicado: (2024)

Byzantine Attica: An Archaeology of Settlement and Landscape, 4th to 12th Centuries. By ElliTzavella. Turnhout: Brepols. 2024. 664 pp. €180. ISBN 978 2 503 61120 4.
por: Lucas McMahon
Publicado: (2025)

Epigenetic Responsibility and Foreseeable Risk
por: Courtney McMahon
Publicado: (2026)

Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
por: Magnino, Lorenzo, et al.
Publicado: (2026)

Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning
por: Wu, Zida, et al.
Publicado: (2025)

Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes
por: van Dalen, Rogier C., et al.
Publicado: (2025)

Streaming Speech-to-Text Translation with a SpeechLLM
por: Parcollet, Titouan, et al.
Publicado: (2026)

An Analysis of Linear Complexity Attention Substitutes with BEST-RQ
por: Whetten, Ryan, et al.
Publicado: (2024)

Towards Early Prediction of Self-Supervised Speech Model Performance
por: Whetten, Ryan, et al.
Publicado: (2025)