{"id":"https://openalex.org/W4372260188","doi":"https://doi.org/10.1109/icassp49357.2023.10096580","title":"SingNet: a real-time Singing Voice beat and Downbeat Tracking System","display_name":"SingNet: a real-time Singing Voice beat and Downbeat Tracking System","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260188","doi":"https://doi.org/10.1109/icassp49357.2023.10096580"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004301078","display_name":"Mojtaba Heydari","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mojtaba Heydari","raw_affiliation_strings":["University of Rochester,Rochester,NY,USA","University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["University of Rochester,Rochester,NY,USA","University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester,Rochester,NY,USA","University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8772928714752197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7672805786132812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6976310014724731},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.47905051708221436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.455799400806427},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.45284876227378845},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.42748168110847473},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.41282880306243896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3731732964515686},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.18580040335655212},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11644509434700012},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09855860471725464},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08496567606925964}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8772928714752197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672805786132812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6976310014724731},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.47905051708221436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.455799400806427},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.45284876227378845},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.42748168110847473},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.41282880306243896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3731732964515686},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.18580040335655212},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11644509434700012},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09855860471725464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08496567606925964},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W75292264","https://openalex.org/W1835965142","https://openalex.org/W2156063659","https://openalex.org/W2350911425","https://openalex.org/W2404298818","https://openalex.org/W2405656250","https://openalex.org/W2573660531","https://openalex.org/W2773636018","https://openalex.org/W2796571515","https://openalex.org/W2902164989","https://openalex.org/W2903493144","https://openalex.org/W2936217452","https://openalex.org/W2984379537","https://openalex.org/W3037798801","https://openalex.org/W3126416163","https://openalex.org/W3170942659","https://openalex.org/W3172640350","https://openalex.org/W3183383888","https://openalex.org/W3203140070","https://openalex.org/W3209984917","https://openalex.org/W3213726885","https://openalex.org/W4221161747","https://openalex.org/W4224918587","https://openalex.org/W4226300471","https://openalex.org/W4294312979","https://openalex.org/W4297847268","https://openalex.org/W4302065815","https://openalex.org/W6603166286","https://openalex.org/W6638699884","https://openalex.org/W6713195707","https://openalex.org/W6732361153","https://openalex.org/W6746760656","https://openalex.org/W6756419834","https://openalex.org/W6779709467","https://openalex.org/W6800044299","https://openalex.org/W6810768903","https://openalex.org/W6842368590","https://openalex.org/W6844204944"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W1989212443","https://openalex.org/W2103644279","https://openalex.org/W4302986566","https://openalex.org/W1968585197","https://openalex.org/W2135362996","https://openalex.org/W4247544095","https://openalex.org/W2122155275","https://openalex.org/W2012949382"],"abstract_inverted_index":{"Singing":[0],"voice":[1],"beat":[2],"and":[3,14,27,41,60,87,133],"downbeat":[4],"tracking":[5],"posses":[6],"several":[7],"applications":[8],"in":[9,44,92],"automatic":[10],"music":[11],"production,":[12],"analysis":[13],"manipulation.":[15],"Among":[16],"them,":[17],"some":[18],"require":[19],"real-time":[20,48],"processing,":[21,49],"such":[22,54],"as":[23,55],"live":[24],"performance":[25,123],"processing":[26],"auto-accompaniment":[28],"for":[29],"singing":[30,45,90],"inputs.":[31],"This":[32],"task":[33],"is":[34],"challenging":[35],"owing":[36],"to":[37,57,63,108],"the":[38,61,65,72,80,85,110,122,129,138,150],"non-trivial":[39],"rhythmic":[40],"harmonic":[42],"patterns":[43],"signals.":[46],"For":[47],"it":[50],"introduces":[51],"further":[52],"constraints":[53],"inaccessibility":[56],"future":[58],"data":[59,107],"impossibility":[62],"correct":[64,109],"previous":[66],"results":[67],"that":[68,83,103,145],"are":[69],"inconsistent":[70],"with":[71,128,137],"latter":[73],"ones.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,95],"introduce":[79],"first":[81],"system":[82],"tracks":[84],"beats":[86],"downbeats":[88],"of":[89,118],"voices":[91],"real-time.":[93],"Specifically,":[94],"propose":[96],"a":[97,115],"novel":[98],"dynamic":[99],"particle":[100],"filtering":[101],"approach":[102,148],"incorporates":[104],"offline":[105],"historical":[106],"online":[111],"inference":[112],"by":[113,152],"using":[114],"variable":[116],"number":[117],"particles.":[119],"We":[120],"evaluate":[121],"on":[124],"two":[125],"datasets:":[126],"GTZAN":[127],"separated":[130],"vocal":[131,140],"tracks,":[132],"an":[134],"in-house":[135],"dataset":[136],"original":[139],"stems.":[141],"Experimental":[142],"result":[143],"demonstrates":[144],"our":[146],"proposed":[147],"outperforms":[149],"baseline":[151],"3\u20135%.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
