{"total":61,"rows":[{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2206.05408","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","created":"2022-06-11","cited_by_count":42,"area":"diffusion"},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35,"area":null},{"id":"2112.09312","title":"MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling","created":"2021-12-17","cited_by_count":32,"area":null},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29,"area":null},{"id":"2407.08428","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2108.03456","title":"A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis","created":"2021-08-07","cited_by_count":18,"area":null},{"id":"2101.04884","title":"Piano Skills Assessment","created":"2021-01-13","cited_by_count":16,"area":null},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14,"area":null},{"id":"2208.06169","title":"DDX7: Differentiable FM Synthesis of Musical Instrument Sounds","created":"2022-08-12","cited_by_count":13,"area":null},{"id":"2407.04822","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","created":"2024-07-05","cited_by_count":13,"area":null},{"id":"2107.05050","title":"Neural Waveshaping Synthesis","created":"2021-07-11","cited_by_count":12,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2408.00196","title":"Combining audio control and style transfer using latent diffusion","created":"2024-07-31","cited_by_count":10,"area":"diffusion"},{"id":"2207.10776","title":"Auto-regressive Image Synthesis with Integrated Quantization","created":"2022-07-21","cited_by_count":9,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2109.02096","title":"Timbre Transfer with Variational Auto Encoding and Cycle-Consistent Adversarial Networks","created":"2021-09-05","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":"2502.17726","title":"The GigaMIDI Dataset with Features for Expressive Music Performance Detection","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2205.05871","title":"Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio","created":"2022-05-12","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":"2510.15148","title":"XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2402.15569","title":"Toward Fully Self-Supervised Multi-Pitch Estimation","created":"2024-02-23","cited_by_count":5,"area":null},{"id":"2111.10003","title":"Differentiable Wavetable Synthesis","created":"2021-11-19","cited_by_count":4,"area":null},{"id":"2202.00200","title":"Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds","created":"2022-02-01","cited_by_count":4,"area":null},{"id":"2309.02405","title":"Generating Realistic Images from In-the-wild Sounds","created":"2023-09-05","cited_by_count":4,"area":null},{"id":"2409.10995","title":"SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.21254","title":"Vision-to-Music Generation: A Survey","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2504.00837","title":"A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2505.15559","title":"Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2107.00231","title":"Audiovisual Singing Voice Separation","created":"2021-07-01","cited_by_count":3,"area":null},{"id":"2203.12829","title":"AIMusicGuru: Music Assisted Human Pose Correction","created":"2022-03-24","cited_by_count":3,"area":null},{"id":"2309.15717","title":"Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2406.06375","title":"MOSA: Music Motion with Semantic Annotation Dataset for Cross-Modal Music Processing","created":"2024-06-10","cited_by_count":3,"area":null},{"id":"2510.00771","title":"UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching","created":"2025-10-01","cited_by_count":3,"area":"diffusion"},{"id":"2306.10684","title":"Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding","created":"2023-06-19","cited_by_count":2,"area":null},{"id":"2409.03715","title":"Applications and Advances of Artificial Intelligence in Music Generation:A Review","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2502.10154","title":"Video Soundtrack Generation by Aligning Emotions and Temporal Boundaries","created":"2025-02-14","cited_by_count":2,"area":null},{"id":"2503.07352","title":"Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2509.26604","title":"Video Object Segmentation-Aware Audio Generation","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2511.14250","title":"Count The Notes: Histogram-Based Supervision for Automatic Music Transcription","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2608.22236","title":"MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models","created":"2026-08-23","cited_by_count":2,"area":null},{"id":"2112.04947","title":"Automated Side Channel Analysis of Media Software with Manifold Learning","created":"2021-12-09","cited_by_count":1,"area":null},{"id":"2402.06810","title":"Evaluating Co-Creativity using Total Information Flow","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2509.23759","title":"VioPTT: Violin Technique-Aware Transcription from Synthetic Data Augmentation","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2511.21247","title":"The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.04343","title":"Summary of The Inaugural Music Source Restoration Challenge","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2608.11576","title":"Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2107.04235","title":"Blind Source Separation in Polyphonic Music Recordings Using Deep Neural Networks Trained via Policy Gradients","created":"2021-07-09","cited_by_count":0,"area":null},{"id":"2111.07140","title":"The Pseudo Projection Operator: Applications of Deep Learning to Projection Based Filtering in Non-Trivial Frequency Regimes","created":"2021-11-13","cited_by_count":0,"area":null},{"id":"2305.12868","title":"NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2310.05821","title":"Pre-trained Spatial Priors on Multichannel NMF for Music Source Separation","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2505.17823","title":"Source Separation of Small Classical Ensembles: Challenges and Opportunities","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.23371","title":"Investigating an Overfitting and Degeneration Phenomenon in Self-Supervised Multi-Pitch Estimation","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2512.15532","title":"A Conditioned UNet for Music Source Separation","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2609.31652","title":"Open-Qwen-Music: An Auditable Framework for LLM-Based Music Composition and Diffusion Rendering","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.33265","title":"SCISSOR: Score-Conditioned Instrument Source Separation for Orchestral Recordings","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.00607","title":"End-to-End Historical Music Restoration in Latent Space","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}