mlsanityData to 7 Oct 2026

BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics

arXiv 2403.10380 ↗First posted 15 Mar 2024cs.SD cs.AI eess.AScited by 36

Not on the map. Why?

Abstract (arXiv)

Deep learning (DL) has greatly advanced audio classification, yet the field is limited by the scarcity of large-scale benchmark datasets that have propelled progress in other domains. While AudioSet is a pivotal step to bridge this gap as a universal-domain dataset, its restricted accessibility and limited range of evaluation use cases challenge its role as the sole resource. Therefore, we introduce BirdSet, a large-scale benchmark dataset for audio classification focusing on avian bioacoustics. BirdSet surpasses AudioSet with over 6,800 recording hours (uparrow!17%) from nearly 10,000 classes (uparrow!18×) for training and more than 400 hours (uparrow!7×) across eight strongly labeled evaluation datasets. It serves as a versatile resource for use cases such as multi-label classification, covariate shift or self-supervised learning. We benchmark six well-known DL models in multi-label classification across three distinct training scenarios and outline further evaluation use cases in audio classification. We host our dataset on Hugging Face for easy accessibility and offer an extensive codebase to reproduce our results.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 34 of its 92 references that are in the map. First posted on arXiv 15 Mar 2024.

Builds on

34 of 92 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2022A ConvNet for the 2020scited by 3,545
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2018Datasheets for Datasetscited by 1,371
  9. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  10. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 641
  11. 2021AST: Audio Spectrogram Transformercited by 634
  12. 2021Datasets: A Community Library for Natural Language Processingcited by 526
22 more
  1. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 378
  2. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 339
  3. 2022Masked Autoencoders that Listencited by 271
  4. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  5. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  6. 2019Deep Learning for Audio Signal Processingcited by 92
  7. 2021Computational bioacoustics with deep learning: a review and roadmapcited by 78
  8. 2024EAT: Self-Supervised Pre-Training with Efficient Audio Transformercited by 52
  9. 2023Epic-Sounds: A Large-scale Dataset of Actions That Soundcited by 47
  10. 2018Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challengecited by 44
  11. 2022BEANS: The Benchmark of Animal Soundscited by 37
  12. 2021Improving Bird Classification with Unsupervised Sound Separationcited by 25
  13. 2022MetaAudio: A Few-Shot Audio Classification Benchmarkcited by 24
  14. 2023BIRB: A Generalization Benchmark for Information Retrieval in Bioacousticscited by 19
  15. 2018NIPS4Bplus: a richly annotated birdsong audio datasetcited by 14
  16. 2023ActiveGLAE: A Benchmark for Deep Active Learning with Transformerscited by 14
  17. 2020SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Contextcited by 12
  18. 2021Who calls the shots? Rethinking Few-Shot Learning for Audiocited by 11
  19. 2023Self-Supervised Learning for Few-Shot Bird Sound Classificationcited by 11
  20. 2023Unsupervised classification to improve the quality of a bird song recording datasetcited by 10
  21. 2021ARCA23K: An audio dataset for investigating open-set label noisecited by 3
  22. 2023Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformerscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 12; 2026: 22.

36 papers.

Sort:

  1. 2025Can Masked Autoencoders Also Listen to Birds?cited by 26
  2. 2025Perch 2.0: The Bittern Lesson for Bioacousticscited by 25
  3. 2024animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacousticscited by 14
  4. 2025Foundation Models for Bioacoustics -- a Comparative Reviewcited by 11
  5. 2024Towards Deep Active Learning in Avian Bioacousticscited by 10
  6. 2026Massive Sound Embedding Benchmark (MSEB)cited by 9
  7. 2025Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classificationcited by 7
  8. 2025AVEX: What Matters for Animal Vocalization Encodingcited by 5
  9. 2026Finding Needles in the Haystack: Transductive Active Labeling in Ecologycited by 3
  10. 2026Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddingscited by 2
  11. 2026Determinantal point process sampling for bioacoustic active learningcited by 2
  12. 2026MetaPerch: Learning from metadata for bioacoustics foundation modelscited by 2
24 more
  1. 2025Localized time-frequency representation learning for bioacoustic classification in complex soundscapescited by 1
  2. 2025WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizationscited by 1
  3. 2025Uncertainty Calibration of Multi-Label Bird Sound Classifierscited by 1
  4. 2025Data-Efficient Self-Supervised Algorithms for Fine-Grained Birdsong Analysiscited by 1
  5. 2025WhAM: Towards A Translative Model of Sperm Whale Vocalizationcited by 1
  6. 2026Multi-layer attentive probing improves transfer of audio representations for bioacousticscited by 1
  7. 2026Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Studycited by 1
  8. 2026BioDCASE: Active Learning for Bioacousticscited by 1
  9. 2025SounDiT: Geo-Contextual Soundscape-to-Landscape Generationcited by 0
  10. 2025Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classificationcited by 0
  11. 2026Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrievalcited by 0
  12. 2026Zwitscherkasten -- DIY Audiovisual bird monitoringcited by 0
  13. 2026BAT: Better Audio Transformer Guided by Convex Gated Probingcited by 0
  14. 2026Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Datacited by 0
  15. 2026A strongly annotated passive acoustic dataset for tropical bird monitoringcited by 0
  16. 2026Time-frequency localization of bird calls in dense soundscapescited by 0
  17. 2026Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Typescited by 0
  18. 2026Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026cited by 0
  19. 2026Efficient Passive Acoustic Monitoring of Killer Whales Using a Two-Stage Detection and Ecotype Classification Cascadecited by 0
  20. 2026Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognitioncited by 0
  21. 2026MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Trainingcited by 0
  22. 2026Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inferencecited by 0
  23. 2026OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizationscited by 0
  24. 2026A Strength-Monotonic Law for Domain Alignment in Frozen-Embedding Bioacoustic Classificationcited by 0