{"total":20,"rows":[{"id":"2311.10057","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","created":"2023-11-16","cited_by_count":68,"area":null},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"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":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2308.15090","title":"Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?","created":"2023-08-29","cited_by_count":3,"area":null},{"id":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","cited_by_count":3,"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":"2407.05782","title":"Sequential Contrastive Audio-Visual Learning","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2506.04376","title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2407.10328","title":"The Interpretation Gap in Text-to-Music Generation Models","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2408.09269","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2504.03329","title":"Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2507.20036","title":"Improving Audio Classification by Transitioning from Zero- to Few-Shot","created":"2025-07-26","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":"2505.21025","title":"Text-Queried Audio Source Separation via Hierarchical Modeling","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2509.09717","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2606.05857","title":"Forgive or forget: Understanding the context of hate in audio retrieval systems","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}