{"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/metrical-accent-aware-vocal-onset-detection","title":"Metrical-accent Aware Vocal Onset Detection in Polyphonic Audio","arxiv_id":"1707.06163","date":"2017-07-19","proceeding":null,"authors":["Georgi Dzhambazov","Andre Holzapfel","Ajay Srinivasamurthy","Xavier Serra"],"abstract":"The goal of this study is the automatic detection of onsets of the singing\nvoice in polyphonic audio recordings. Starting with a hypothesis that the\nknowledge of the current position in a metrical cycle (i.e. metrical accent)\ncan improve the accuracy of vocal note onset detection, we propose a novel\nprobabilistic model to jointly track beats and vocal note onsets. The proposed\nmodel extends a state of the art model for beat and meter tracking, in which\na-priori probability of a note at a specific metrical accent interacts with the\nprobability of observing a vocal note onset. We carry out an evaluation on a\nvaried collection of multi-instrument datasets from two music traditions\n(English popular music and Turkish makam) with different types of metrical\ncycles and singing styles. Results confirm that the proposed model reasonably\nimproves vocal note onset detection accuracy compared to a baseline model that\ndoes not take metrical position into account.","url_abs":"http://arxiv.org/abs/1707.06163v1","url_pdf":"http://arxiv.org/pdf/1707.06163v1.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":"metrical-accent-aware-vocal-onset-detection","repo_url":"https://github.com/georgid/lakh_vocal_segments_dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"metrical-accent-aware-vocal-onset-detection","repo_url":"https://github.com/georgid/madmom","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"metrical-accent-aware-vocal-onset-detection","repo_url":"https://github.com/georgid/pypYIN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"onset-detection","task_name":"Onset Detection"},{"task_slug":null,"task_name":"Position"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}