{"total":54,"rows":[{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727,"area":null},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643,"area":null},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339,"area":null},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169,"area":null},{"id":"2304.13731","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","created":"2023-04-24","cited_by_count":145,"area":"lr"},{"id":"2404.09956","title":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","created":"2024-04-15","cited_by_count":97,"area":"diffusion"},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82,"area":null},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2103.15375","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","created":"2021-03-29","cited_by_count":33,"area":null},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2212.10888","title":"A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability","created":"2022-12-21","cited_by_count":31,"area":null},{"id":"2208.09913","title":"A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective","created":"2022-08-21","cited_by_count":27,"area":null},{"id":"2306.04186","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","created":"2023-06-07","cited_by_count":25,"area":"distill"},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16,"area":null},{"id":"2107.09887","title":"An overview of mixing augmentation methods and augmentation strategies","created":"2021-07-21","cited_by_count":14,"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":"2211.13189","title":"ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2201.02354","title":"GenLabel: Mixup Relabeling using Generative Models","created":"2022-01-07","cited_by_count":10,"area":null},{"id":"2103.02420","title":"Multi-view Audio and Music Classification","created":"2021-03-03","cited_by_count":8,"area":null},{"id":"2211.01202","title":"Human-in-the-Loop Mixup","created":"2022-11-02","cited_by_count":8,"area":null},{"id":"2203.12314","title":"Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices","created":"2022-03-23","cited_by_count":7,"area":null},{"id":"2103.03483","title":"Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2112.09172","title":"An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classification","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2302.07315","title":"A dataset for Audio-Visual Sound Event Detection in Movies","created":"2023-02-14","cited_by_count":5,"area":null},{"id":"2103.01929","title":"SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification","created":"2021-03-02","cited_by_count":4,"area":null},{"id":"2110.04964","title":"Label-Occurrence-Balanced Mixup for Long-tailed Recognition","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2307.09286","title":"FlexiAST: Flexibility is What AST Needs","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2101.10280","title":"Deep Epidemiological Modeling by Black-box Knowledge Distillation: An Accurate Deep Learning Model for COVID-19","created":"2021-01-20","cited_by_count":3,"area":"distill"},{"id":"2106.13913","title":"Midpoint Regularization: from High Uncertainty Training to Conservative Classification","created":"2021-06-26","cited_by_count":3,"area":null},{"id":"2108.06128","title":"Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices","created":"2021-08-13","cited_by_count":3,"area":null},{"id":"2211.02820","title":"A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification","created":"2022-11-05","cited_by_count":3,"area":null},{"id":"2302.02092","title":"Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics","created":"2023-02-04","cited_by_count":3,"area":null},{"id":"2308.13201","title":"Deep Active Audio Feature Learning in Resource-Constrained Environments","created":"2023-08-25","cited_by_count":3,"area":null},{"id":"2303.04104","title":"An Inception-Residual-Based Architecture with Multi-Objective Loss for Detecting Respiratory Anomalies","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2102.13360","title":"A Universal Model for Cross Modality Mapping by Relational Reasoning","created":"2021-02-26","cited_by_count":1,"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":"2110.11144","title":"RCT: Random Consistency Training for Semi-supervised Sound Event Detection","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2206.06057","title":"Low-complexity deep learning frameworks for acoustic scene classification","created":"2022-06-13","cited_by_count":1,"area":null},{"id":"2206.13392","title":"Remote Sensing Image Classification using Transfer Learning and Attention Based Deep Neural Network","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2210.08610","title":"Robust, General, and Low Complexity Acoustic Scene Classification Systems and An Effective Visualization for Presenting a Sound Scene Context","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2303.00510","title":"A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2309.13227","title":"Importance of negative sampling in weak label learning","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2411.16121","title":"DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2503.15576","title":"A Bird Song Detector for improving bird identification through Deep Learning: a case study from Do\\~nana","created":"2025-03-19","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":"2211.14395","title":"Deep Learning Training Procedure Augmentations","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2305.09463","title":"Low-complexity deep learning frameworks for acoustic scene classification using teacher-student scheme and multiple spectrograms","created":"2023-05-16","cited_by_count":0,"area":"distill"},{"id":"2309.13373","title":"Asca: less audio data is more insightful","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2403.16464","title":"Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2501.01921","title":"Structural and Statistical Audio Texture Knowledge Distillation for Acoustic Classification","created":"2025-01-03","cited_by_count":0,"area":"distill"},{"id":"2511.15675","title":"MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2604.19652","title":"Environmental Sound Deepfake Detection Using Deep-Learning Framework","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.20893","title":"Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.14287","title":"Acoustic UAV Detection in Battlefield Scenarios: Handling Noise, Domain Shift, and Weak Labels","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}