{"total":44,"rows":[{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2403.10380","title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","created":"2024-03-15","cited_by_count":36,"area":null},{"id":"2404.06393","title":"MuPT: A Generative Symbolic Music Pretrained Transformer","created":"2024-04-09","cited_by_count":33,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2508.01277","title":"Foundation Models for Bioacoustics -- a Comparative Review","created":"2025-08-02","cited_by_count":11,"area":null},{"id":"2504.05684","title":"TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2509.24901","title":"Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","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":"2506.10423","title":"PAL: Probing Audio Encoders via LLMs -- Audio Information Transfer into LLMs","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2507.16696","title":"FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive Representation","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2511.22344","title":"Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2408.15667","title":"Towards reliable respiratory disease diagnosis based on cough sounds and vision transformers","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2409.16005","title":"Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2506.10312","title":"AC/DC: LLM-based Audio Comprehension via Dialogue Continuation","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2507.02666","title":"ASDA: Audio Spectrogram Differential Attention Mechanism for Self-Supervised Representation Learning","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2508.15334","title":"An Enhanced Audio Feature Tailored for Anomalous Sound Detection Based on Pre-trained Models","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2509.16649","title":"AISTAT lab system for DCASE2025 Task6: Language-based audio retrieval","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2510.19368","title":"AMAuT: A Flexible and Efficient Multiview Audio Transformer Framework Trained from Scratch","created":"2025-10-22","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":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.06444","title":"USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.14791","title":"From Physics to Representation: Audio Learning with Synthetic Pre-training via Procedural Generation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2609.26460","title":"Can We Predict Anomaly Detection Performance from Embedding-Space Geometry?","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2505.11020","title":"Classifying Shelf Life Quality of Pineapples by Combining Audio and Visual Features","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2508.14689","title":"ECHO: Frequency-aware Hierarchical Encoding for Variable-length Signals","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.12845","title":"Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.26291","title":"Representation-Based Data Quality Audits for Audio","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.03637","title":"AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.15180","title":"BEAT2AASIST model with layer fusion for ESDD 2026 Challenge","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.21612","title":"Representation-Regularized Convolutional Audio Transformer for Audio Understanding","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.16305","title":"BAT: Better Audio Transformer Guided by Convex Gated Probing","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.13749","title":"Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.18932","title":"Tadabur: A Large-Scale Quran Audio Dataset","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2607.04526","title":"Training-Free Model Selection and Domain-Aware Score Calibration for First-Shot Anomalous Sound Detection","created":"2026-07-05","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":"2608.19863","title":"Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners","created":"2026-08-20","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":"2609.15215","title":"Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.27362","title":"Anomaly-Free Self-Optimization via AUC Bounds","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.05852","title":"RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}