{"id":"https://openalex.org/W4401109651","doi":"https://doi.org/10.1109/taslp.2024.3426303","title":"A Two-Stage Audio-Visual Fusion Piano Transcription Model Based on the Attention Mechanism","display_name":"A Two-Stage Audio-Visual Fusion Piano Transcription Model Based on the Attention Mechanism","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401109651","doi":"https://doi.org/10.1109/taslp.2024.3426303"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3426303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426303","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088125172","display_name":"Yuqing Li","orcid":"https://orcid.org/0009-0001-3621-8859"},"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":"Yuqing Li","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet 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, Wuhan, China","institution_ids":[]},{"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/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":["Hubei Key Laboratory of Smart Internet 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, Wuhan, China","institution_ids":[]},{"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/A5037018884","display_name":"Ruimin Wu","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":"Ruimin Wu","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet 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, Wuhan, China","institution_ids":[]},{"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, 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, Wuhan, China","institution_ids":[]},{"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/A5108962320","display_name":"Wenqing Cheng","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":"Wenqing Cheng","raw_affiliation_strings":["Hubei Key Laboratory of Smart Internet 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, Wuhan, China","institution_ids":[]},{"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/A5088125172"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.3577,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53536263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3618","last_page":"3630"},"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":0.9952999949455261,"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":"Diverse Musicological Studies","score":0.984499990940094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541080713272095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6409124135971069},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6253938674926758},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6045876741409302},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5307918190956116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5011460781097412},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4634663164615631},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4181100130081177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3251626193523407},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1275453269481659},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.12008547782897949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541080713272095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6409124135971069},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6253938674926758},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6045876741409302},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5307918190956116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011460781097412},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4634663164615631},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4181100130081177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3251626193523407},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1275453269481659},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.12008547782897949},{"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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3426303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426303","pdf_url":null,"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":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G57838077","display_name":null,"funder_award_id":"62277019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1975962343","https://openalex.org/W2017578549","https://openalex.org/W2044505737","https://openalex.org/W2054770976","https://openalex.org/W2087064593","https://openalex.org/W2096482524","https://openalex.org/W2101897555","https://openalex.org/W2110007838","https://openalex.org/W2131774270","https://openalex.org/W2148899569","https://openalex.org/W2152937398","https://openalex.org/W2182291269","https://openalex.org/W2194775991","https://openalex.org/W2198584637","https://openalex.org/W2279376057","https://openalex.org/W2299180476","https://openalex.org/W2505399031","https://openalex.org/W2550393250","https://openalex.org/W2560023338","https://openalex.org/W2620021285","https://openalex.org/W2788575351","https://openalex.org/W2792764867","https://openalex.org/W2906214917","https://openalex.org/W2921484047","https://openalex.org/W2964346351","https://openalex.org/W2982083293","https://openalex.org/W3016096605","https://openalex.org/W3081064203","https://openalex.org/W3131500599","https://openalex.org/W3160694286","https://openalex.org/W3206008172","https://openalex.org/W3209419355","https://openalex.org/W3213036384","https://openalex.org/W4224947526","https://openalex.org/W4239510810","https://openalex.org/W4285367240","https://openalex.org/W4285483408","https://openalex.org/W4313594098","https://openalex.org/W4381186350","https://openalex.org/W4383988462","https://openalex.org/W4385245566","https://openalex.org/W4385485032","https://openalex.org/W6714030504","https://openalex.org/W6728773792","https://openalex.org/W6729470292","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6749825310","https://openalex.org/W6755182157","https://openalex.org/W6780316881","https://openalex.org/W6781533629","https://openalex.org/W6798855526","https://openalex.org/W6846575651","https://openalex.org/W6854061045"],"related_works":["https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W4362512397","https://openalex.org/W587444722","https://openalex.org/W2022713566","https://openalex.org/W2336023324","https://openalex.org/W633023889"],"abstract_inverted_index":{"Piano":[0],"transcription":[1,33,64,73,181],"is":[2,43],"a":[3,44,68,100],"significant":[4,175],"problem":[5],"in":[6,115],"the":[7,55,77,87,91,116,120,139,147,153,157,162,179],"field":[8],"of":[9,18,47,58,156,172],"music":[10,19],"information":[11,85],"retrieval,":[12],"aiming":[13],"to":[14,111,129,145],"obtain":[15],"symbolic":[16],"representations":[17],"from":[20,86],"captured":[21],"audio":[22,37,82,97,104],"or":[23,38],"visual":[24,39,84,101,121],"signals.":[25],"Previous":[26],"research":[27],"has":[28],"mainly":[29],"focused":[30],"on":[31,50,76,161],"single-modal":[32,180],"methods":[34],"using":[35],"either":[36],"information,":[40],"yet":[41],"there":[42],"small":[45],"number":[46],"studies":[48],"based":[49,75],"audio-visual":[51,70],"fusion.":[52],"To":[53],"leverage":[54],"complementary":[56],"advantages":[57],"both":[59,81,124],"modalities":[60,151],"and":[61,83,99,126,132,152],"achieve":[62],"higher":[63],"accuracy,":[65],"we":[66,94,142],"propose":[67,95],"two-stage":[69],"fusion":[71],"piano":[72,88],"model":[74,98,105,122,168],"attention":[78,110],"mechanism,":[79],"utilizing":[80],"performance.":[89],"In":[90,138],"first":[92],"stage,":[93,141],"an":[96,170],"model.":[102],"The":[103],"utilizes":[106],"frequency":[107,117],"domain":[108],"sparse":[109],"capture":[112],"harmonic":[113],"relationships":[114,155],"domain,":[118],"while":[119],"includes":[123],"CNN":[125],"Transformer":[127],"branches":[128],"merge":[130],"local":[131],"global":[133],"features":[134],"at":[135],"different":[136,150],"resolutions.":[137],"second":[140],"employ":[143],"cross-attention":[144],"learn":[146],"correlations":[148],"between":[149],"temporal":[154],"sequences.":[158],"Experimental":[159],"results":[160],"OMAPS2":[163],"dataset":[164],"show":[165],"that":[166],"our":[167],"achieves":[169],"F1-score":[171],"98.60%,":[173],"demonstrating":[174],"improvement":[176],"compared":[177],"with":[178],"models.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}