{"id":"https://openalex.org/W4224917360","doi":"https://doi.org/10.1109/icassp43922.2022.9746684","title":"Musicyolo: A Sight-Singing Onset/Offset Detection Framework Based on Object Detection Instead of Spectrum Frames","display_name":"Musicyolo: A Sight-Singing Onset/Offset Detection Framework Based on Object Detection Instead of Spectrum Frames","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917360","doi":"https://doi.org/10.1109/icassp43922.2022.9746684"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746684","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/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":["Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074","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":["Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074","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":["Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074","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":["Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Hubei Provincial Key Laboratory of Smart Internet Technology,School of Electronic Information and Communications,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002684652"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.4916,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56492891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9972000122070312,"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":0.9968000054359436,"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/offset","display_name":"Offset (computer science)","score":0.8508029580116272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.701423168182373},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6297786235809326},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5950155258178711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5628979206085205},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5327762365341187},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.48650163412094116},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.44504523277282715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3658114969730377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.287655234336853},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14509546756744385},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11204835772514343},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07293158769607544}],"concepts":[{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.8508029580116272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701423168182373},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6297786235809326},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5950155258178711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5628979206085205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5327762365341187},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.48650163412094116},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.44504523277282715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3658114969730377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.287655234336853},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14509546756744385},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11204835772514343},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07293158769607544},{"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/icassp43922.2022.9746684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746684","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2005787925","https://openalex.org/W2029337446","https://openalex.org/W2107328928","https://openalex.org/W2191779130","https://openalex.org/W2294039222","https://openalex.org/W2396885260","https://openalex.org/W2402883000","https://openalex.org/W2407685581","https://openalex.org/W2586947700","https://openalex.org/W2635912764","https://openalex.org/W2771824692","https://openalex.org/W2939641110","https://openalex.org/W2942551338","https://openalex.org/W2950547518","https://openalex.org/W2963492800","https://openalex.org/W2972476119","https://openalex.org/W3095395784","https://openalex.org/W3098454764","https://openalex.org/W3160649916","https://openalex.org/W3167721750","https://openalex.org/W3184439416","https://openalex.org/W4293584584","https://openalex.org/W6697015887","https://openalex.org/W6713313301","https://openalex.org/W6714030504","https://openalex.org/W6733426572","https://openalex.org/W6746379959","https://openalex.org/W6750227808","https://openalex.org/W6755182157","https://openalex.org/W6796058780","https://openalex.org/W6798838024"],"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/W2390529913"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"MusicYOLO":[5,56,85,111],"based":[6],"on":[7,104],"object":[8,61],"detection":[9,43,54,76,95,103,116],"to":[10],"detect":[11],"the":[12,19,25,40,51,58,63,74,84,105,113],"onset":[13,23,94],"and":[14,31,96],"offset":[15,102],"in":[16,62],"singing":[17,119],"for":[18,118],"first":[20],"time.":[21],"The":[22,79],"of":[24,35,67,93,101],"vocal":[26],"is":[27,112],"not":[28,46],"as":[29,33],"stable":[30],"clear":[32],"that":[34,83,110],"musical":[36],"instruments,":[37],"which":[38,108],"makes":[39],"frame-based":[41],"onset/offset":[42,53,75,115],"methods":[44],"often":[45],"work":[47],"well.":[48],"Compared":[49],"with":[50],"previous":[52],"methods,":[55],"detects":[57],"whole":[59],"note":[60],"spectrogram":[64],"image":[65],"instead":[66],"transient":[68],"frame":[69],"features":[70],"around":[71],"onset/offset,":[72],"improving":[73],"performance":[77],"significantly.":[78],"experiment":[80],"results":[81],"show":[82],"framework":[86,117],"has":[87],"obtained":[88],"a":[89,97],"94.16%":[90],"F1":[91,99],"score":[92,100],"91.35%":[98],"ISMIR2014":[106],"dataset,":[107],"proves":[109],"state-of-the-art":[114],"situation.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
