{"total":50,"rows":[{"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":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134,"area":null},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2405.04883","title":"FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2506.19085","title":"Benchmarking Music Generation Models and Metrics via Human Preference Studies","created":"2025-06-23","cited_by_count":15,"area":null},{"id":"2403.11780","title":"Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt","created":"2024-03-18","cited_by_count":12,"area":null},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2512.10403","title":"BRACE: A Benchmark for Robust Audio Caption Quality Evaluation","created":"2025-12-11","cited_by_count":7,"area":null},{"id":"2402.03710","title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2406.07012","title":"Bridging Language Gaps in Audio-Text Retrieval","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2510.05542","title":"Sci-Phi: A Large Language Model Spatial Audio Descriptor","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2410.16505","title":"Do Audio-Language Models Understand Linguistic Variations?","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2409.13676","title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2409.16937","title":"Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labeling","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2501.15900","title":"Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2508.15418","title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2511.15131","title":"CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2407.05782","title":"Sequential Contrastive Audio-Visual Learning","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2510.13244","title":"MotionBeat: Motion-Aligned Music Representation via Embodied Contrastive Learning and Bar-Equivariant Contact-Aware Encoding","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2412.17306","title":"Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2501.05787","title":"MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2501.09877","title":"CLAP-S: Support Set Based Adaptation for Downstream Fiber-optic Acoustic Recognition","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2506.06537","title":"Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models","created":"2025-06-06","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":"2510.06204","title":"Modulation Discovery with Differentiable Digital Signal Processing","created":"2025-10-07","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":"2601.05011","title":"Leveraging Prediction Entropy for Automatic Prompt Weighting in Zero-Shot Audio-Language Classification","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2607.03806","title":"Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2608.02397","title":"Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2409.15545","title":"Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2512.00496","title":"CACARA: Cross-Modal Alignment Leveraging a Text-Centric Approach for Cost-Effective Multimodal and Multilingual Learning","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.15118","title":"WavLink: Compact Audio-Text Embeddings with a Global Whisper Token","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.03190","title":"Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.20267","title":"ATIR: Towards Audio-Text Interleaved Contextual Retrieval","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.20847","title":"Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.06615","title":"FIGMA: Towards FIne-Grained Music retrievAl","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.17542","title":"Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08526","title":"A Quantized Native Runtime for On-Device Semantic Audio Generation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.24786","title":"Unlocking Spatial Grounding in Large Audio-Visual Retrieval models","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.04479","title":"AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.32016","title":"VoiceNet: Fine-Grained Voice Understanding Beyond Emotion at Scale","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.02148","title":"Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}