{"id":"https://openalex.org/W4385485032","doi":"https://doi.org/10.1109/icasspw59220.2023.10193618","title":"A CRNN-GCN Piano Transcription Model Based On Audio And Skeleton Features","display_name":"A CRNN-GCN Piano Transcription Model Based On Audio And Skeleton Features","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385485032","doi":"https://doi.org/10.1109/icasspw59220.2023.10193618"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5100379930","display_name":"Yuqing Li","orcid":"https://orcid.org/0000-0001-7493-9297"},"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":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","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":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","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":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,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,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100628705","display_name":"Wenqing Chen","orcid":"https://orcid.org/0000-0002-8739-2216"},"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 Chen","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100379930"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.6113,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64964006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"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":0.9937000274658203,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9934999942779541,"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/transcription","display_name":"Transcription (linguistics)","score":0.7652345895767212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7089142203330994},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5419647693634033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46453744173049927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44834890961647034},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.44473621249198914},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4154369831085205},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15643206238746643},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06304040551185608},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06163334846496582}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7652345895767212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089142203330994},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5419647693634033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46453744173049927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44834890961647034},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.44473621249198914},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4154369831085205},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15643206238746643},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06304040551185608},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06163334846496582},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2110007838","https://openalex.org/W2182291269","https://openalex.org/W2299180476","https://openalex.org/W2407685581","https://openalex.org/W2519887557","https://openalex.org/W2788575351","https://openalex.org/W2792764867","https://openalex.org/W2921484047","https://openalex.org/W2950547518","https://openalex.org/W2963076818","https://openalex.org/W2964015378","https://openalex.org/W3016096605","https://openalex.org/W3017343282","https://openalex.org/W3127314429","https://openalex.org/W4285367240","https://openalex.org/W4287072584","https://openalex.org/W4293775315","https://openalex.org/W4320028097","https://openalex.org/W6714030504","https://openalex.org/W6745851314","https://openalex.org/W6749825310","https://openalex.org/W6755182157","https://openalex.org/W6783580442","https://openalex.org/W6798855526","https://openalex.org/W6846575651"],"related_works":["https://openalex.org/W3120625693","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W3164677766","https://openalex.org/W4375869439","https://openalex.org/W2783215299","https://openalex.org/W1627686592","https://openalex.org/W4378446399","https://openalex.org/W1974546149","https://openalex.org/W4285367382"],"abstract_inverted_index":{"Piano":[0],"transcription":[1,26,35,42,81],"is":[2,31,110],"a":[3,24],"fundamental":[4],"problem":[5],"in":[6],"music":[7],"information":[8],"retrieval,":[9],"which":[10,30,64,109],"aims":[11],"to":[12,78],"infer":[13],"the":[14,18,51,73,88,91,101,104,111],"note":[15],"sequence":[16],"from":[17,50,57],"piano":[19,25],"multimedia.":[20],"This":[21],"paper":[22],"proposes":[23],"model":[27,36,43],"named":[28],"CRNN-GCN,":[29],"fused":[32],"with":[33],"audio":[34],"Onset":[37],"and":[38,40,53,69,94,98],"Frames(CRNN)":[39],"visual":[41],"Graph":[44],"Convolutional":[45],"Network(GCN).":[46],"CRNN":[47,93],"extracts":[48,55],"features":[49,56,74],"audio,":[52],"GCN":[54,95],"hand":[58],"skeletons":[59],"rather":[60],"than":[61],"video":[62,67],"frames,":[63],"effectively":[65],"reduces":[66],"memory":[68],"computational":[70],"complexity.":[71],"All":[72],"are":[75,96],"then":[76],"integrated":[77],"obtain":[79],"better":[80],"results.":[82],"On":[83],"our":[84],"self-built":[85],"dataset":[86],"OMAPS2,":[87],"F1-scores":[89],"of":[90,103],"single-modal":[92],"89.98%":[97],"61.63%,":[99],"while":[100],"F1-score":[102],"multi-modal":[105],"CRNNGCN":[106],"reaches":[107],"92.06%,":[108],"best":[112],"result":[113],"at":[114],"present.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}