{"total":18,"rows":[{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2501.09291","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2407.07801","title":"AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning","created":"2024-07-10","cited_by_count":6,"area":null},{"id":"2312.03632","title":"Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2403.14438","title":"A Multimodal Approach to Device-Directed Speech Detection with Large Language Models","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2409.01201","title":"EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2406.14701","title":"Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2409.01160","title":"Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2502.05435","title":"Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2601.04658","title":"LAMB: LLM-based Audio Captioning with Modality Gap Bridging via Cauchy-Schwarz Divergence","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2409.09866","title":"S2Cap: A Benchmark and a Baseline for Singing Style Captioning","created":"2024-09-15","cited_by_count":0,"area":null},{"id":"2501.03183","title":"Classifier-Guided Captioning Across Modalities","created":"2025-01-03","cited_by_count":0,"area":null},{"id":"2603.26804","title":"The Language of Touch: Translating Vibrations into Text with Dual-Branch Learning","created":"2026-03-26","cited_by_count":0,"area":null}],"next_cursor":null}