{"total":51,"rows":[{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2508.04665","title":"Perch 2.0: The Bittern Lesson for Bioacoustics","created":"2025-08-06","cited_by_count":26,"area":null},{"id":"2308.04978","title":"Transferable Models for Bioacoustics with Human Language Supervision","created":"2023-08-09","cited_by_count":21,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2406.01253","title":"animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2508.01277","title":"Foundation Models for Bioacoustics -- a Comparative Review","created":"2025-08-02","cited_by_count":11,"area":null},{"id":"2307.06860","title":"AnuraSet: A dataset for benchmarking Neotropical anuran calls identification in passive acoustic monitoring","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2501.05987","title":"Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2504.06710","title":"Clustering and novel class recognition: evaluating bioacoustic deep learning feature extractors","created":"2025-04-09","cited_by_count":7,"area":null},{"id":"2512.03219","title":"Perch 2.0 transfers 'whale' to underwater tasks","created":"2025-12-02","cited_by_count":7,"area":null},{"id":"2409.12634","title":"Exploring bat song syllable representations in self-supervised audio encoders","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2508.11845","title":"AVEX: What Matters for Animal Vocalization Encoding","created":"2025-08-15","cited_by_count":5,"area":null},{"id":"2402.03269","title":"ISPA: Inter-Species Phonetic Alphabet for Transcribing Animal Sounds","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2503.02389","title":"Robust detection of overlapping bioacoustic sound events","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2509.04166","title":"Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2402.17775","title":"WhaleNet: a Novel Deep Learning Architecture for Marine Mammals Vocalizations on Watkins Marine Mammal Sound Database","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2409.08673","title":"Acoustic identification of individual animals with hierarchical contrastive learning","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2502.00344","title":"FinchGPT: a Transformer based language model for birdsong analysis","created":"2025-02-01","cited_by_count":2,"area":null},{"id":"2503.00296","title":"Synthetic data enables context-aware bioacoustic sound event detection","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2511.05171","title":"Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2601.08358","title":"Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddings","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2604.11560","title":"bacpipe: a Python package to make bioacoustic deep learning models accessible","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2606.12503","title":"Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2401.17805","title":"Biospheric AI","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2402.15985","title":"Phonetic and Lexical Discovery of a Canine Language using HuBERT","created":"2024-02-25","cited_by_count":1,"area":null},{"id":"2508.10230","title":"No Free Lunch from Audio Pretraining in Bioacoustics: A Benchmark Study of Embeddings","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2511.12158","title":"Data-Efficient Self-Supervised Algorithms for Fine-Grained Birdsong Analysis","created":"2025-11-15","cited_by_count":1,"area":null},{"id":"2512.02206","title":"WhAM: Towards A Translative Model of Sperm Whale Vocalization","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2605.00225","title":"From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.10494","title":"Multi-layer attentive probing improves transfer of audio representations for bioacoustics","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.14031","title":"Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2509.09198","title":"GmSLM : Generative Marmoset Spoken Language Modeling","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.11168","title":"An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2511.16849","title":"Better audio representations are more brain-like: linking model-brain alignment with performance in downstream auditory tasks","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2602.03817","title":"Adaptive Evidence Weighting for Audio-Spatiotemporal Fusion","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.13330","title":"Zwitscherkasten -- DIY Audiovisual bird monitoring","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.27936","title":"Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.07903","title":"BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.21143","title":"CoarseSoundNet: Building a reliable model for ecological soundscape analysis","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.02341","title":"Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.16084","title":"Rhythm of the Deep: Two-tier acoustic organization of sperm-whale codas from click waveforms to second-order sequence dependence","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.03304","title":"Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.14474","title":"Can Tokens Compete? Token Representations against Supervised CNN Backbones for BirdCLEF+ 2026","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.02104","title":"Uncertainty-Aware Crossmodal Fusion for Classification of Animal Behavior","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.01792","title":"Efficient Passive Acoustic Monitoring of Killer Whales Using a Two-Stage Detection and Ecotype Classification Cascade","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.11986","title":"Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.16612","title":"Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal repertoires using frozen audio encoders","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.20408","title":"Xeno-Interpretability: Investigating the Alien Minds of LLMs","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.27409","title":"Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.34839","title":"OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.09737","title":"A Strength-Monotonic Law for Domain Alignment in Frozen-Embedding Bioacoustic Classification","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}