{"total":72,"rows":[{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226,"area":null},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213,"area":null},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176,"area":null},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2205.03433","title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","created":"2022-05-06","cited_by_count":62,"area":null},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49,"area":null},{"id":"2204.02874","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","created":"2022-04-06","cited_by_count":39,"area":null},{"id":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"area":null},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27,"area":null},{"id":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22,"area":null},{"id":"2208.00061","title":"UAVM: Towards Unifying Audio and Visual Models","created":"2022-07-29","cited_by_count":20,"area":null},{"id":"2303.10757","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","created":"2023-03-19","cited_by_count":16,"area":null},{"id":"2403.19638","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","created":"2024-03-28","cited_by_count":14,"area":null},{"id":"2210.00943","title":"Simple Pooling Front-ends For Efficient Audio Classification","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2401.14405","title":"Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities","created":"2024-01-25","cited_by_count":7,"area":null},{"id":"2406.10254","title":"Towards Signal Processing In Large Language Models","created":"2024-06-10","cited_by_count":7,"area":null},{"id":"2506.01890","title":"CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2307.00079","title":"Dataset balancing can hurt model performance","created":"2023-06-30","cited_by_count":5,"area":null},{"id":"2409.15383","title":"Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics","created":"2024-09-21","cited_by_count":5,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2311.01526","title":"ATGNN: Audio Tagging Graph Neural Network","created":"2023-11-02","cited_by_count":4,"area":null},{"id":"2207.07773","title":"Segment-level Metric Learning for Few-shot Bioacoustic Event Detection","created":"2022-07-15","cited_by_count":3,"area":null},{"id":"2210.11328","title":"Play It Back: Iterative Attention for Audio Recognition","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2304.11472","title":"A Comparative Study of Pre-trained Speech and Audio Embeddings for Speech Emotion Recognition","created":"2023-04-22","cited_by_count":3,"area":null},{"id":"2305.00104","title":"MMViT: Multiscale Multiview Vision Transformers","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2305.12712","title":"LEAN: Light and Efficient Audio Classification Network","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2310.15648","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2410.00511","title":"Pre-training with Synthetic Patterns for Audio","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2412.11449","title":"Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2511.00256","title":"NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2110.06999","title":"Study of positional encoding approaches for Audio Spectrogram Transformers","created":"2021-10-13","cited_by_count":1,"area":null},{"id":"2204.07763","title":"UFRC: A Unified Framework for Reliable COVID-19 Detection on Crowdsourced Cough Audio","created":"2022-04-16","cited_by_count":1,"area":null},{"id":"2211.12195","title":"Ontology-aware Learning and Evaluation for Audio Tagging","created":"2022-11-22","cited_by_count":1,"area":null},{"id":"2301.10056","title":"Side Eye: Characterizing the Limits of POV Acoustic Eavesdropping from Smartphone Cameras with Rolling Shutters and Movable Lenses","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2308.07221","title":"AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2309.13972","title":"Audio classification with Dilated Convolution with Learnable Spacings","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2401.10544","title":"AAT: Adapting Audio Transformer for Various Acoustics Recognition Tasks","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2501.03464","title":"LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2502.07971","title":"Hierarchical Retrieval at Scale: Bridging Transparency and Efficiency","created":"2025-02-11","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":"2204.11479","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2303.10446","title":"Content Adaptive Front End For Audio Classification","created":"2023-03-18","cited_by_count":0,"area":null},{"id":"2308.14105","title":"Unified and Dynamic Graph for Temporal Character Grouping in Long Videos","created":"2023-08-27","cited_by_count":0,"area":null},{"id":"2309.08751","title":"Diverse Audio Embeddings -- Bringing Features Back Outperforms CLAP!","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2309.13373","title":"Asca: less audio data is more insightful","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2312.16228","title":"Deformable Audio Transformer for Audio Event Detection","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2402.10100","title":"Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2407.10828","title":"Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Method","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2410.03146","title":"Bridging the Gap between Text, Audio, Image, and Any Sequence: A Novel Approach using Gloss-based Annotation","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2503.11373","title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2503.21826","title":"Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.03388","title":"Cross-Modal Urban Sensing: Evaluating Sound-Vision Alignment Across Street-Level and Aerial Imagery","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2510.21388","title":"Compressing Quaternion Convolutional Neural Networks for Audio Classification","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2512.00496","title":"CACARA: Cross-Modal Alignment Leveraging a Text-Centric Approach for Cost-Effective Multimodal and Multilingual Learning","created":"2025-11-29","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":"2603.25476","title":"How Class Ontology and Data Scale Affect Audio Transfer Learning","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2606.15751","title":"Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.22218","title":"An Analysis of Untrained Deep Reservoir Networks for Audio Surveillance","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.22952","title":"Domain-incremental audio classification using domain-specific experts and prototype classifier","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.31587","title":"ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization in Audio-Language Models","created":"2026-06-30","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":"2609.14730","title":"Parameter isolation with domain-specific experts for incremental audio classification","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}