{"total":24,"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":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"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":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2309.10667","title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","created":"2023-09-19","cited_by_count":14,"area":null},{"id":"2408.09481","title":"PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2024-08-18","cited_by_count":13,"area":null},{"id":"2312.10144","title":"Data-Efficient Multimodal Fusion on a Single GPU","created":"2023-12-15","cited_by_count":11,"area":null},{"id":"2405.10084","title":"Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2406.07012","title":"Bridging Language Gaps in Audio-Text Retrieval","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2211.07737","title":"Describing emotions with acoustic property prompts for speech emotion recognition","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2311.01615","title":"FLAP: Fast Language-Audio Pre-training","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2310.02298","title":"Prompting Audios Using Acoustic Properties For Emotion Representation","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2310.11830","title":"CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2311.02482","title":"Generalized zero-shot audio-to-intent classification","created":"2023-11-04","cited_by_count":1,"area":null},{"id":"2408.13068","title":"On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning","created":"2024-08-23","cited_by_count":1,"area":null},{"id":"2505.23732","title":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2510.14249","title":"Do Joint Language-Audio Embeddings Encode Perceptual Timbre Semantics?","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.08399","title":"Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment","created":"2025-11-11","cited_by_count":0,"area":null}],"next_cursor":null}