TweetyBERT: Automated parsing of birdsong through self-supervised machine learning

2026/03/03 by George Vengrovski, Miranda Hulsey-Vincent, Melissa A. Bemrose +1 · 1 voice
Biochemistry, Genetics and Molecular Biology · Computer Science · Social Sciences · #Animal Vocal Communication and Behavior #Authorship Attribution and Profiling #Language and cultural evolution

paper · doi:10.1016/j.patter.2025.101491

openalex publication_date 2026/03/03 · openalex created_date 2026/03/04 · openalex updated_date 2026/07/23

Abstract

Publisher of over 50 scientific journals across the life, physical, earth, and health sciences, both independently and in partnership with scientific societies including Cell, Neuron, Immunity, Current Biology, AJHG, and the Trends Journals.

Citations

• Array programming with NumPy
• Classification of pig calls produced from birth to slaughter according to their emotional valence and context of production
• Perch 2.0: The Bittern Lesson for Bioacoustics
• Can Masked Autoencoders Also Listen to Birds?
• Byte Latent Transformer: Patches Scale Better Than Tokens
• Algorithmic Capabilities of Random Transformers
• A-JEPA: Joint-Embedding Predictive Architecture Can Listen
• Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?
• LLaMA: Open and Efficient Foundation Language Models
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
• Characterizing the structure of mouse behavior using Motion Sequencing
• AVES: Animal Vocalization Encoder based on Self-Supervision
• Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
• Learning Transferable Visual Models From Natural Language Supervision
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
• Conformer: Convolution-augmented Transformer for Speech Recognition
• Conformer: Convolution-augmented Transformer for Speech Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Visualizing and Measuring the Geometry of BERT
• Self-Attention with Relative Position Representations
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Mixed Precision Training
• Attention Is All You Need
• Understanding intermediate layers using linear classifier probes
• Gaussian Error Linear Units (GELUs)
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Adam: A Method for Stochastic Optimization
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Discussions

• Interesting use of AI methods of self-supervised learning, to analyze canary song. Authors demo on seasonal changes Just published in Patterns: doi.org/10.1016/j.pa... Code: github.com/georgevenve [bsky, 6 points, 1 comments]

Related

• TweeNLP: A Twitter Exploration Portal for Natural Language Processing
• Lynn Margulis, 1938–2011
• chatter: a Python library for applying information theory and AI/ML models to animal communication
• Using AI to write scholarly publications
• Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026