{"id":"https://openalex.org/W4311167650","doi":"https://doi.org/10.1109/taslp.2022.3221005","title":"MusicYOLO: A Vision-Based Framework for Automatic Singing Transcription","display_name":"MusicYOLO: A Vision-Based Framework for Automatic Singing Transcription","publication_year":2022,"publication_date":"2022-11-10","ids":{"openalex":"https://openalex.org/W4311167650","doi":"https://doi.org/10.1109/taslp.2022.3221005"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3221005","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3221005","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09944977.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09944977.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002684652","display_name":"Xianke Wang","orcid":"https://orcid.org/0000-0001-7037-9800"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xianke Wang","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077362727","display_name":"Bowen Tian","orcid":"https://orcid.org/0000-0003-4885-8922"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Tian","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101538141","display_name":"Weiming Yang","orcid":"https://orcid.org/0000-0003-2795-6662"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Yang","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814324","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0003-4705-7189"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056643192","display_name":"Wenqing Cheng","orcid":"https://orcid.org/0000-0001-7840-1195"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqing Cheng","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002684652"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":1.1915,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78244561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"229","last_page":"241"},"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":0.9966999888420105,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/transcription","display_name":"Transcription (linguistics)","score":0.7728334665298462},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7225558757781982},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6683101654052734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6482230424880981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6080363988876343},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5952446460723877},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5362491011619568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46923524141311646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3962988257408142},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10311326384544373}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7728334665298462},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7225558757781982},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6683101654052734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6482230424880981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6080363988876343},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5952446460723877},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5362491011619568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46923524141311646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3962988257408142},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10311326384544373},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3221005","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3221005","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09944977.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3221005","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3221005","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/09944977.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4731737681","display_name":null,"funder_award_id":"2021YFC3340803","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6624196571","display_name":null,"funder_award_id":"2021YFC","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8704888226","display_name":null,"funder_award_id":"61877060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311167650.pdf","grobid_xml":"https://content.openalex.org/works/W4311167650.grobid-xml"},"referenced_works_count":87,"referenced_works":["https://openalex.org/W198589515","https://openalex.org/W200102888","https://openalex.org/W639708223","https://openalex.org/W1484767381","https://openalex.org/W1526336542","https://openalex.org/W1550987960","https://openalex.org/W1558000412","https://openalex.org/W1650531274","https://openalex.org/W1778811406","https://openalex.org/W1901129140","https://openalex.org/W1970578576","https://openalex.org/W1975079546","https://openalex.org/W1990449877","https://openalex.org/W1990908299","https://openalex.org/W2005122913","https://openalex.org/W2005787925","https://openalex.org/W2029337446","https://openalex.org/W2034300186","https://openalex.org/W2034995162","https://openalex.org/W2038509404","https://openalex.org/W2042390666","https://openalex.org/W2065529590","https://openalex.org/W2090431713","https://openalex.org/W2091425152","https://openalex.org/W2097423688","https://openalex.org/W2100989275","https://openalex.org/W2105068979","https://openalex.org/W2107328928","https://openalex.org/W2107831318","https://openalex.org/W2108771579","https://openalex.org/W2118774185","https://openalex.org/W2119110418","https://openalex.org/W2124120139","https://openalex.org/W2143039550","https://openalex.org/W2152151492","https://openalex.org/W2172073751","https://openalex.org/W2180653312","https://openalex.org/W2184687474","https://openalex.org/W2191779130","https://openalex.org/W2206275834","https://openalex.org/W2294039222","https://openalex.org/W2295707189","https://openalex.org/W2341412280","https://openalex.org/W2354870669","https://openalex.org/W2407685581","https://openalex.org/W2497516627","https://openalex.org/W2518618011","https://openalex.org/W2562770010","https://openalex.org/W2577202280","https://openalex.org/W2586947700","https://openalex.org/W2635912764","https://openalex.org/W2635922319","https://openalex.org/W2654517624","https://openalex.org/W2755000466","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2962866891","https://openalex.org/W2963037989","https://openalex.org/W2963158330","https://openalex.org/W2964066126","https://openalex.org/W2975281968","https://openalex.org/W2989926340","https://openalex.org/W3011176162","https://openalex.org/W3017343282","https://openalex.org/W3027082420","https://openalex.org/W3037149862","https://openalex.org/W3103314642","https://openalex.org/W3152594694","https://openalex.org/W3160649916","https://openalex.org/W3168054270","https://openalex.org/W3184439416","https://openalex.org/W4211104227","https://openalex.org/W6632833597","https://openalex.org/W6638009197","https://openalex.org/W6639824700","https://openalex.org/W6676245417","https://openalex.org/W6678849920","https://openalex.org/W6686280200","https://openalex.org/W6687152286","https://openalex.org/W6697015887","https://openalex.org/W6714030504","https://openalex.org/W6732421929","https://openalex.org/W6733426572","https://openalex.org/W6747331233","https://openalex.org/W6768334536","https://openalex.org/W6798838024","https://openalex.org/W7066299598"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Automatic":[0],"singing":[1,18],"transcription":[2,58,79,122,139],"(AST),":[3],"which":[4,75,141],"refers":[5],"to":[6,36],"the":[7,11,17,32,42,56,77,88,94,108,121,125,134,143],"process":[8],"of":[9,21],"inferring":[10],"onset,":[12],"offset,":[13],"and":[14,40,44,54,93],"pitch":[15,95],"from":[16],"audio,":[19],"is":[20,73,85,97,142],"great":[22],"significance":[23],"in":[24,131],"music":[25],"information":[26],"retrieval.":[27],"Most":[28],"AST":[29,69],"models":[30],"use":[31],"convolutional":[33],"neural":[34],"network":[35],"extract":[37],"spectral":[38],"features":[39],"predict":[41],"onset":[43],"offset":[45],"moments":[46],"separately.":[47],"The":[48,82],"frame-level":[49],"probabilities":[50],"are":[51,60],"inferred":[52],"first,":[53],"then":[55],"note-level":[57,78],"results":[59,80],"obtained":[61],"through":[62],"post-processing.":[63],"In":[64],"this":[65,132],"paper,":[66,133],"a":[67,100],"new":[68],"framework":[70],"called":[71],"MusicYOLO":[72,109,135],"proposed,":[74],"obtains":[76],"directly.":[81],"onset/offset":[83,116],"detection":[84,90],"based":[86],"on":[87],"object":[89],"model":[91],"YOLOX,":[92],"labeling":[96],"completed":[98],"by":[99],"spectrogram":[101],"peak":[102],"search.":[103],"Compared":[104],"with":[105],"previous":[106],"methods,":[107],"detects":[110],"note":[111],"objects":[112],"rather":[113],"than":[114],"isolated":[115],"moments,":[117],"thus":[118],"greatly":[119],"enhancing":[120],"performance.":[123],"On":[124],"sight-singing":[126],"vocal":[127],"dataset":[128],"(SSVD)":[129],"established":[130],"achieves":[136],"an":[137],"84.60%":[138],"F1-score,":[140],"state-of-the-art":[144],"method.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}