{"total":25,"rows":[{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29,"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":"2204.03594","title":"Heterogeneous Target Speech Separation","created":"2022-04-07","cited_by_count":13,"area":null},{"id":"2104.09946","title":"A cappella: Audio-visual Singing Voice Separation","created":"2021-04-20","cited_by_count":12,"area":null},{"id":"2210.16472","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","created":"2022-10-29","cited_by_count":11,"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":"2206.10805","title":"Jointist: Joint Learning for Multi-instrument Transcription and Its Applications","created":"2022-06-22","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":"2211.05927","title":"Optimal Condition Training for Target Source Separation","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2201.09592","title":"Unsupervised Music Source Separation Using Differentiable Parametric Source Models","created":"2022-01-24","cited_by_count":4,"area":null},{"id":"2112.00209","title":"Environmental Sound Extraction Using Onomatopoeic Words","created":"2021-12-01","cited_by_count":3,"area":null},{"id":"2302.00286","title":"Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2104.13553","title":"AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries","created":"2021-04-28","cited_by_count":2,"area":null},{"id":"2110.05313","title":"Unsupervised Source Separation via Bayesian Inference in the Latent Domain","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2309.00410","title":"Selective Scene Text Removal","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2507.01339","title":"User-guided Generative Source Separation","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2203.04197","title":"Locate This, Not That: Class-Conditioned Sound Event DOA Estimation","created":"2022-03-08","cited_by_count":1,"area":null},{"id":"2308.09411","title":"Metadata Improves Segmentation Through Multitasking Elicitation","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2501.06236","title":"Data-Driven Radio Propagation Modeling using Graph Neural Networks","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2111.12516","title":"LightSAFT: Lightweight Latent Source Aware Frequency Transform for Source Separation","created":"2021-11-24","cited_by_count":0,"area":null},{"id":"2206.12132","title":"SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2212.00380","title":"Proceedings of the 2nd International Workshop on Reading Music Systems","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2307.14609","title":"Complete and separate: Conditional separation with missing target source attribute completion","created":"2023-07-27","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":"2607.08863","title":"Clean2FX: Label-conditioned modeling for clean-to-effect guitar audio transformations","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}