{"total":226,"rows":[{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344,"area":"diffusion"},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324,"area":"diffusion"},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197,"area":null},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181,"area":null},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146,"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":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2404.10301","title":"Long-form music generation with latent diffusion","created":"2024-04-16","cited_by_count":89,"area":"diffusion"},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2508.16930","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","created":"2025-08-23","cited_by_count":46,"area":"diffusion"},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"area":null},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2506.21448","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","created":"2025-06-26","cited_by_count":34,"area":"lr"},{"id":"2211.13929","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","created":"2022-11-25","cited_by_count":31,"area":"distill"},{"id":"2311.00613","title":"Controllable Music Production with Diffusion Models and Guidance Gradients","created":"2023-11-01","cited_by_count":29,"area":"diffusion"},{"id":"2211.04772","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","created":"2022-11-09","cited_by_count":27,"area":"distill"},{"id":"2307.14335","title":"WavJourney: Compositional Audio Creation with Large Language Models","created":"2023-07-26","cited_by_count":27,"area":null},{"id":"2306.04186","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","created":"2023-06-07","cited_by_count":25,"area":"distill"},{"id":"2502.15602","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2210.14648","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","cited_by_count":23,"area":null},{"id":"2406.02178","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","created":"2024-06-04","cited_by_count":19,"area":"ssm"},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17,"area":null},{"id":"2504.14906","title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","created":"2025-04-21","cited_by_count":17,"area":null},{"id":"2506.12222","title":"SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes","created":"2025-06-13","cited_by_count":16,"area":"mllm"},{"id":"2303.16541","title":"Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation","created":"2023-03-29","cited_by_count":15,"area":null},{"id":"2304.10520","title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","created":"2023-04-20","cited_by_count":15,"area":null},{"id":"2402.16998","title":"What Do Language Models Hear? Probing for Auditory Representations in Language Models","created":"2024-02-26","cited_by_count":15,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2505.08175","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","created":"2025-05-13","cited_by_count":14,"area":null},{"id":"2211.13189","title":"ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2301.09595","title":"Zorro: the masked multimodal transformer","created":"2023-01-23","cited_by_count":13,"area":null},{"id":"2407.03648","title":"High Fidelity Text-Guided Music Editing via Single-Stage Flow Matching","created":"2024-07-04","cited_by_count":13,"area":"diffusion"},{"id":"2409.15157","title":"LoVA: Long-form Video-to-Audio Generation","created":"2024-09-23","cited_by_count":13,"area":"diffusion"},{"id":"2203.06760","title":"CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification","created":"2022-03-13","cited_by_count":12,"area":"distill"},{"id":"2508.00733","title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","created":"2025-08-01","cited_by_count":12,"area":"diffusion"},{"id":"2305.07499","title":"Device-Robust Acoustic Scene Classification via Impulse Response Augmentation","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2503.00084","title":"InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation","created":"2025-02-28","cited_by_count":11,"area":"diffusion"},{"id":"2506.12199","title":"ViSAGe: Video-to-Spatial Audio Generation","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2601.02731","title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","created":"2026-01-06","cited_by_count":11,"area":null},{"id":"2405.13636","title":"Audio Mamba: Pretrained Audio State Space Model For Audio Tagging","created":"2024-05-22","cited_by_count":10,"area":"ssm"},{"id":"2407.14364","title":"Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio","created":"2024-07-19","cited_by_count":10,"area":null},{"id":"2510.12000","title":"UALM: Unified Audio Language Model for Understanding, Generation and Reasoning","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2309.11845","title":"TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification","created":"2023-09-21","cited_by_count":9,"area":null},{"id":"2404.10989","title":"FairSSD: Understanding Bias in Synthetic Speech Detectors","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2405.18503","title":"SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation","created":"2024-05-28","cited_by_count":9,"area":"diffusion"},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9,"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":"2506.18729","title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2507.16343","title":"Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2511.18833","title":"PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation","created":"2025-11-24","cited_by_count":9,"area":"lr"},{"id":"2503.10719","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2406.18747","title":"A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2408.08673","title":"MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2409.06135","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","created":"2024-09-10","cited_by_count":7,"area":null},{"id":"2209.12900","title":"The Efficacy of Self-Supervised Speech Models for Audio Representations","created":"2022-09-26","cited_by_count":6,"area":null},{"id":"2304.03323","title":"DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection","created":"2023-04-06","cited_by_count":6,"area":null},{"id":"2308.04258","title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2411.01135","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","created":"2024-11-02","cited_by_count":6,"area":null},{"id":"2412.09428","title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation","created":"2024-12-12","cited_by_count":6,"area":null},{"id":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2306.17424","title":"Audio Embeddings as Teachers for Music Classification","created":"2023-06-30","cited_by_count":5,"area":"distill"},{"id":"2406.07676","title":"FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation","created":"2024-06-11","cited_by_count":5,"area":"inference"},{"id":"2406.19135","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability","created":"2024-06-27","cited_by_count":5,"area":null},{"id":"2409.15383","title":"Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics","created":"2024-09-21","cited_by_count":5,"area":null},{"id":"2505.12154","title":"Learning to Highlight Audio by Watching Movies","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2505.16195","title":"SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2510.02110","title":"SoundReactor: Frame-level Online Video-to-Audio Generation","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2210.07546","title":"Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2211.13956","title":"Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers","created":"2022-11-25","cited_by_count":4,"area":null},{"id":"2307.09286","title":"FlexiAST: Flexibility is What AST Needs","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2311.01526","title":"ATGNN: Audio Tagging Graph Neural Network","created":"2023-11-02","cited_by_count":4,"area":null},{"id":"2401.04023","title":"Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2406.02315","title":"An Independence-promoting Loss for Music Generation with Language Models","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2407.16643","title":"Synthesizer Sound Matching Using Audio Spectrogram Transformers","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2409.13049","title":"DiffSSD: A Diffusion-Based Dataset For Speech Forensics","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2503.22208","title":"DeepSound-V1: Start to Think Step-by-Step in the Audio Generation from Videos","created":"2025-03-28","cited_by_count":4,"area":"lr"},{"id":"2510.13344","title":"UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE","created":"2025-10-15","cited_by_count":4,"area":"moe"},{"id":"2510.21581","title":"Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2603.15597","title":"AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.01929","title":"Woosh: A Sound Effects Foundation Model","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2210.11328","title":"Play It Back: Iterative Attention for Audio Recognition","created":"2022-10-20","cited_by_count":3,"area":null}],"next_cursor":"100"}