{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-cappella-audio-visual-singing-voice","title":"A cappella: Audio-visual Singing Voice Separation","arxiv_id":"2104.09946","date":"2021-04-20","proceeding":null,"authors":["Juan F. Montesinos","Venkatesh S. Kadandale","Gloria Haro"],"abstract":"The task of isolating a target singing voice in music videos has useful applications. In this work, we explore the single-channel singing voice separation problem from a multimodal perspective, by jointly learning from audio and visual modalities. To do so, we present Acappella, a dataset spanning around 46 hours of a cappella solo singing videos sourced from YouTube. We also propose an audio-visual convolutional network based on graphs which achieves state-of-the-art singing voice separation results on our dataset and compare it against its audio-only counterpart, U-Net, and a state-of-the-art audio-visual speech separation model. We evaluate the models in the following challenging setups: i) presence of overlapping voices in the audio mixtures, ii) the target voice set to lower volume levels in the mix, and iii) combination of i) and ii). The third one being the most challenging evaluation setup. We demonstrate that our model outperforms the baseline models in the singing voice separation task in the most challenging evaluation setup. The code, the pre-trained models, and the dataset are publicly available at https://ipcv.github.io/Acappella/able at https://ipcv.github.io/Acappella/","url_abs":"https://arxiv.org/abs/2104.09946v3","url_pdf":"https://arxiv.org/pdf/2104.09946v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-cappella-audio-visual-singing-voice","repo_url":"https://github.com/JuanFMontesinos/Acappella-YNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-cappella-audio-visual-singing-voice","repo_url":"https://github.com/JuanFMontesinos/y-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"music-source-separation","task_name":"Music Source Separation"},{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[{"slug":"acappella","name":"Acappella","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.09946","atlas_url":"https://app.syntology.ai/?focus=2104.09946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09946"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JuanFMontesinos/Acappella-YNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JuanFMontesinos/y-net","reach":{"status":"ok"}}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"f51e6ad9c7104a5a","entry":"rescale","repo":"JuanFMontesinos/Acappella-YNet","repo_kind":"official","path":"VnBSS/models/y_net.py","file_url":"https://github.com/JuanFMontesinos/Acappella-YNet/blob/HEAD/VnBSS/models/y_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f51e6ad9c7104a5a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}