{"id":"https://openalex.org/W4285367240","doi":"https://doi.org/10.23919/dafx51585.2021.9768275","title":"An Audio-Visual Fusion Piano Transcription Approach Based on Strategy","display_name":"An Audio-Visual Fusion Piano Transcription Approach Based on Strategy","publication_year":2021,"publication_date":"2021-09-08","ids":{"openalex":"https://openalex.org/W4285367240","doi":"https://doi.org/10.23919/dafx51585.2021.9768275"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.23919/dafx51585.2021.9768275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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":false,"raw_author_name":"Xianke Wang","raw_affiliation_strings":["School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080649483","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-6616-3633"},"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":["School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061780413","display_name":"Juanting Liu","orcid":null},"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":"Juanting Liu","raw_affiliation_strings":["School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,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":["School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069858870","display_name":"Wenqing Cheng","orcid":"https://orcid.org/0009-0000-3452-9170"},"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":["School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.291,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.578233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":67,"max":73},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Audio Signal Classification and Analysis","score":0.9979,"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":"Audio Signal Classification and Analysis","score":0.9979,"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/T13996","display_name":"Ecomusicology and Ethnomusicological Research on Environmental and Cultural Sustainability","score":0.9857,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10515","display_name":"Role of Long Noncoding RNAs in Cancer and Development","score":0.9446,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7561322},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.53335756},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music Information Retrieval","score":0.51683},{"id":"https://openalex.org/keywords/environmental-sound-recognition","display_name":"Environmental Sound Recognition","score":0.513264},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature Extraction","score":0.510857},{"id":"https://openalex.org/keywords/transcriptional-landscape","display_name":"Transcriptional Landscape","score":0.505036},{"id":"https://openalex.org/keywords/audio-event-detection","display_name":"Audio Event Detection","score":0.500969},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4885193}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7561322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259567},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6848042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6161947},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5794506},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.53335756},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4885193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47235736},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34538162},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17346165},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.23919/dafx51585.2021.9768275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61877060"}],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W2002666695","https://openalex.org/W2044505737","https://openalex.org/W2110007838","https://openalex.org/W2182291269","https://openalex.org/W2198584637","https://openalex.org/W2229159429","https://openalex.org/W2299180476","https://openalex.org/W2433636802","https://openalex.org/W2560023338","https://openalex.org/W2587310949","https://openalex.org/W2604292070","https://openalex.org/W2753779507","https://openalex.org/W2788575351","https://openalex.org/W2906214917","https://openalex.org/W2913384670","https://openalex.org/W2921484047","https://openalex.org/W2963163009","https://openalex.org/W3016096605","https://openalex.org/W3081064203","https://openalex.org/W4285367382"],"related_works":["https://openalex.org/W607893370","https://openalex.org/W3214791684","https://openalex.org/W2392133813","https://openalex.org/W2357375963","https://openalex.org/W2353265673","https://openalex.org/W2316271602","https://openalex.org/W2152662039","https://openalex.org/W2145797872","https://openalex.org/W2132659060","https://openalex.org/W2031992971"],"abstract_inverted_index":{"Piano":[0],"transcription":[1,45,56,102,124],"is":[2,30,51,83,108],"a":[3,15,31,43,94],"fundamental":[4],"problem":[5],"in":[6,53,85],"the":[7,55,59,70,79,112,123,134],"field":[8],"of":[9,18,34,58,72],"music":[10],"information":[11],"retrieval.":[12],"At":[13],"present,":[14],"large":[16],"number":[17,33],"transcriptional":[19],"studies":[20],"are":[21,62],"mainly":[22],"based":[23,36,47,104,114,126,136],"on":[24,37,48,98,105,115,127,137],"audio":[25,66],"or":[26],"video,":[27],"yet":[28],"there":[29],"small":[32],"discussion":[35],"audio-visual":[38,77],"fusion.":[39,117,139],"In":[40],"this":[41,86],"paper,":[42],"piano":[44],"model":[46,61,92,103,125],"strategy":[49,90,116,128],"fusion":[50,91,107,129],"proposed,":[52],"which":[54],"results":[57,120,132],"video":[60],"used":[63,75],"to":[64,69],"assist":[65],"transcription.":[67],"Due":[68],"lack":[71],"datasets":[73],"currently":[74],"for":[76],"fusion,":[78],"OMAPS":[80,99],"data":[81],"set":[82],"proposed":[84],"paper.":[87],"Meanwhile,":[88],"our":[89],"achieves":[93,130],"92.07%":[95],"F1":[96],"score":[97],"dataset.":[100],"The":[101,118],"feature":[106,138],"also":[109],"compared":[110],"with":[111],"one":[113,135],"experiment":[119],"show":[121],"that":[122],"better":[131],"than":[133]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4285367240","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2024-11-23T00:23:37.682268","created_date":"2022-07-14"}