{"total":22,"rows":[{"id":"2310.14159","title":"Can Language Models Laugh at YouTube Short-form Videos?","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2505.14705","title":"Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation","created":"2025-05-16","cited_by_count":7,"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":"2310.15648","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2403.19002","title":"Robust Active Speaker Detection in Noisy Environments","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2406.15897","title":"Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval","created":"2024-06-22","cited_by_count":2,"area":null},{"id":"2408.11641","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2410.06927","title":"Spectral and Rhythm Features for Audio Classification with Deep Convolutional Neural Networks","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2306.08010","title":"Domain Information Control at Inference Time for Acoustic Scene Classification","created":"2023-06-13","cited_by_count":1,"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":"2407.15423","title":"Integrating IP Broadcasting with Audio Tags: Workflow and Challenges","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2408.11656","title":"Macformer: Transformer with Random Maclaurin Feature Attention","created":"2024-08-21","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":"2509.00914","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.14049","title":"Comprehensive Evaluation of CNN-Based Audio Tagging Models on Resource-Constrained Devices","created":"2025-09-17","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":"2601.03227","title":"The Sonar Moment: Benchmarking Audio-Language Models in Audio Geo-Localization","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2606.00629","title":"Quality Audio Prototyping: a prototype system for unified sound retrieval and procedural generation","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2609.24791","title":"Detecting Agitation Before Behavioral Escalation in Autistic Youth Through Multimodal Wearable Sensing","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.31024","title":"Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}