{"total":22,"rows":[{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2210.16428","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","created":"2022-10-28","cited_by_count":13,"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":"2311.16509","title":"StyleCap: Automatic Speaking-Style Captioning from Speech Based on Speech and Language Self-supervised Learning Models","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2310.07284","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2409.06223","title":"Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models","created":"2024-09-10","cited_by_count":5,"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":"2212.02033","title":"Towards Generating Diverse Audio Captions via Adversarial Training","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2505.22045","title":"Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2506.00800","title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2407.17716","title":"Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2410.12028","title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation","created":"2024-10-15","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":"2509.12591","title":"MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2309.08141","title":"Audio Difference Learning for Audio Captioning","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2405.11093","title":"AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2607.21424","title":"An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.02343","title":"SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2610.01861","title":"AVSD-Scenes: A Dataset for Audio-Visual Description of Urban Scenes","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}