{"id":"https://openalex.org/W3131432709","doi":"https://doi.org/10.1109/taslp.2021.3061267","title":"Audio-Based Piano Performance Evaluation for Beginners With Convolutional Neural Network and Attention Mechanism","display_name":"Audio-Based Piano Performance Evaluation for Beginners With Convolutional Neural Network and Attention Mechanism","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3131432709","doi":"https://doi.org/10.1109/taslp.2021.3061267","mag":"3131432709"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3061267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3061267","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/A5100372962","display_name":"Weiqing Wang","orcid":"https://orcid.org/0000-0002-8588-7872"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiqing Wang","raw_affiliation_strings":["School of Data and Computer Science at Sun Yat-sen University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science at Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037232759","display_name":"Jin Xiao Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210129003","display_name":"SYSU-CMU International Joint Research Institute","ror":"https://ror.org/02w30ae27","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129003"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Pan","raw_affiliation_strings":["School of SYSU-CMU Joint Institute of Engineering at Sun Yat-sen University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"School of SYSU-CMU Joint Institute of Engineering at Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I4210129003","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110987289","display_name":"Yi Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097173","display_name":"Shandong Yingcai University","ror":"https://ror.org/00qhrkk71","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210097173"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Yi","raw_affiliation_strings":["School of Preschool Education, Shandong Yingcai University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Preschool Education, Shandong Yingcai University, Jinan, China","institution_ids":["https://openalex.org/I4210097173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042329123","display_name":"Zhanmei Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097173","display_name":"Shandong Yingcai University","ror":"https://ror.org/00qhrkk71","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210097173"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanmei Song","raw_affiliation_strings":["School of Preschool Education, Shandong Yingcai University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Preschool Education, Shandong Yingcai University, Jinan, China","institution_ids":["https://openalex.org/I4210097173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Data Science Research Center at Duke Kunshan University, Kunshan, China","School of Computer Science at Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center at Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science at Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100372962"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":2.4685,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89593365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1119","last_page":"1133"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.80983567237854},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.777301013469696},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6868783235549927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6012956500053406},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5683210492134094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5131970047950745},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4643334150314331},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4277421832084656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42075905203819275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4060942232608795},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0800844132900238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80983567237854},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.777301013469696},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6868783235549927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6012956500053406},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5683210492134094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5131970047950745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4643334150314331},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4277421832084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42075905203819275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4060942232608795},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0800844132900238},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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.2021.3061267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3061267","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/G2099609658","display_name":null,"funder_award_id":"61773413","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G262123784","display_name":null,"funder_award_id":"JY-074","funder_id":"https://openalex.org/F4320326182","funder_display_name":"Six Talent Peaks Project in Jiangsu Province"},{"id":"https://openalex.org/G5284168442","display_name":null,"funder_award_id":"BHA160085","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/F4320326182","display_name":"Six Talent Peaks Project in Jiangsu Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W37699876","https://openalex.org/W64868312","https://openalex.org/W169568072","https://openalex.org/W189345193","https://openalex.org/W1819710477","https://openalex.org/W1895577753","https://openalex.org/W1902027874","https://openalex.org/W1902237438","https://openalex.org/W2076608692","https://openalex.org/W2083126990","https://openalex.org/W2096482524","https://openalex.org/W2100816929","https://openalex.org/W2103822047","https://openalex.org/W2105343238","https://openalex.org/W2107800121","https://openalex.org/W2110007838","https://openalex.org/W2129638017","https://openalex.org/W2144994235","https://openalex.org/W2152937398","https://openalex.org/W2157331557","https://openalex.org/W2158983491","https://openalex.org/W2165253089","https://openalex.org/W2191779130","https://openalex.org/W2198584637","https://openalex.org/W2293056991","https://openalex.org/W2313339984","https://openalex.org/W2340348677","https://openalex.org/W2395935897","https://openalex.org/W2406222150","https://openalex.org/W2408697724","https://openalex.org/W2494980014","https://openalex.org/W2509206472","https://openalex.org/W2522399191","https://openalex.org/W2593836007","https://openalex.org/W2613904329","https://openalex.org/W2740270986","https://openalex.org/W2745937295","https://openalex.org/W2772682484","https://openalex.org/W2795298889","https://openalex.org/W2937033898","https://openalex.org/W2950335938","https://openalex.org/W2952111078","https://openalex.org/W2962824709","https://openalex.org/W2962968839","https://openalex.org/W2963403868","https://openalex.org/W2963551352","https://openalex.org/W2964265128","https://openalex.org/W2972944488","https://openalex.org/W3005347330","https://openalex.org/W4240592325","https://openalex.org/W4285719527","https://openalex.org/W4293775315","https://openalex.org/W4385245566","https://openalex.org/W6601523149","https://openalex.org/W6602701445","https://openalex.org/W6606734960","https://openalex.org/W6607768639","https://openalex.org/W6675399557","https://openalex.org/W6675936907","https://openalex.org/W6696869404","https://openalex.org/W6714635449","https://openalex.org/W6725750439","https://openalex.org/W6733936739","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6741559241","https://openalex.org/W6745851314","https://openalex.org/W6746243457","https://openalex.org/W6773842061"],"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/W633023889","https://openalex.org/W2357210383"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"two":[5,57,71,145],"different":[6],"audio-based":[7],"piano":[8,91,139],"performance":[9,39,67,140],"evaluation":[10,141],"systems":[11],"for":[12],"beginners.":[13],"The":[14,42],"first":[15],"is":[16,45,132],"a":[17,66,108,116,136],"sequential":[18],"and":[19,38,51,63],"modularized":[20,105],"system,":[21],"including":[22],"three":[23],"steps:":[24],"Convolutional":[25],"Neural":[26],"Network":[27],"(CNN)-based":[28],"acoustic":[29,58],"feature":[30,59],"extraction,":[31],"matching":[32],"via":[33],"dynamic":[34],"time":[35],"warping":[36],"(DTW),":[37],"score":[40],"regression.":[41],"second":[43],"system":[44,48,106,121,142],"an":[46,124],"end-to-end":[47,120,138],"with":[49,74,143],"CNNs":[50],"the":[52,104],"attention":[53],"mechanism.":[54],"It":[55],"takes":[56],"sequences":[60],"as":[61],"input":[62],"directly":[64],"predicts":[65],"score.":[68],"We":[69],"evaluate":[70],"proposed":[72],"methods":[73],"our":[75],"new":[76],"open-access":[77],"Yingcai":[78],"Piano":[79],"Performance":[80],"Evaluation":[81],"Phase":[82],"III":[83],"Dataset":[84],"(YCU-PPE-III)":[85],"that":[86,103,130],"contains":[87],"more":[88],"than":[89],"2000":[90],"audio":[92,147],"pieces":[93],"recorded":[94],"in":[95,115],"multiple":[96],"real":[97],"test":[98],"sessions.":[99],"Experimental":[100],"results":[101],"show":[102],"achieves":[107,123],"mean":[109],"absolute":[110],"error":[111],"(MAE)":[112],"of":[113,126],"3.79":[114],"0-100-point":[117],"range.":[118],"Another":[119],"also":[122],"MAE":[125],"4.40,":[127],"which":[128],"shows":[129],"it":[131],"possible":[133],"to":[134],"train":[135],"robust":[137],"only":[144],"thousand":[146],"pieces.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}