{"id":"https://openalex.org/W3184438937","doi":"https://doi.org/10.1109/lsp.2021.3099073","title":"Stereo Feature Enhancement and Temporal Information Extraction Network for Automatic Music Transcription","display_name":"Stereo Feature Enhancement and Temporal Information Extraction Network for Automatic Music Transcription","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3184438937","doi":"https://doi.org/10.1109/lsp.2021.3099073","mag":"3184438937"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3099073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3099073","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5018530110","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0003-4665-8142"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340711","display_name":"Yonghui Zhang","orcid":"https://orcid.org/0000-0003-3622-8237"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghui Zhang","raw_affiliation_strings":["WeiXin Group, Tencent, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeiXin Group, Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019082565","display_name":"Yanjun She","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanjun She","raw_affiliation_strings":["Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":"https://orcid.org/0000-0003-2615-1555","affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1977,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78557031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"1500","last_page":"1504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9886000156402588,"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":0.9710000157356262,"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":0.8120548725128174},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6634997129440308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.591692328453064},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.580345094203949},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5336343050003052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4921242594718933},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4608421325683594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4429301619529724},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41319411993026733},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3324253559112549},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1487528383731842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120548725128174},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6634997129440308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.591692328453064},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.580345094203949},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5336343050003052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4921242594718933},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4608421325683594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4429301619529724},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41319411993026733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3324253559112549},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1487528383731842},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2021.3099073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3099073","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G4253300795","display_name":null,"funder_award_id":"61832001","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W89231944","https://openalex.org/W1993845689","https://openalex.org/W2110007838","https://openalex.org/W2122585011","https://openalex.org/W2125838338","https://openalex.org/W2144414181","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2198584637","https://openalex.org/W2293634267","https://openalex.org/W2405656250","https://openalex.org/W2593836007","https://openalex.org/W2725868244","https://openalex.org/W2753779507","https://openalex.org/W2771231137","https://openalex.org/W2771429098","https://openalex.org/W2792764867","https://openalex.org/W2898148140","https://openalex.org/W2938774173","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2963403868","https://openalex.org/W2963551352","https://openalex.org/W2996731350","https://openalex.org/W3008054319","https://openalex.org/W3046154609","https://openalex.org/W3091273176","https://openalex.org/W3132851202","https://openalex.org/W4293775315","https://openalex.org/W4385245566","https://openalex.org/W6603626069","https://openalex.org/W6681236507","https://openalex.org/W6696934422","https://openalex.org/W6733936739","https://openalex.org/W6739901393","https://openalex.org/W6740333300","https://openalex.org/W6745851314","https://openalex.org/W6746269311","https://openalex.org/W6746430418","https://openalex.org/W6749825310","https://openalex.org/W6755182157","https://openalex.org/W6790718468"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2003977768","https://openalex.org/W2910935116","https://openalex.org/W2157165686","https://openalex.org/W1975359510","https://openalex.org/W4316036082"],"abstract_inverted_index":{"As":[0],"a":[1,19,23,43,59,113],"challenging":[2],"task":[3],"of":[4,73,96,125],"audio":[5,21,32],"processing,":[6],"automatic":[7],"music":[8,27,137],"transcription":[9],"(AMT)":[10],"attracts":[11],"increasing":[12],"attention":[13],"recently,":[14],"which":[15,49,92,118],"aims":[16],"to":[17,22,42,69,121],"convert":[18],"raw":[20],"symbolic":[24],"representation.":[25],"Nowadays,":[26],"recordings":[28],"are":[29],"usually":[30],"stereo":[31,40,60,74],"files.":[33],"Many":[34],"previous":[35],"studies":[36],"simply":[37],"average":[38],"the":[39,133],"signal":[41,45],"mono":[44],"when":[46],"processing":[47,89],"data,":[48,91],"sacrifices":[50],"some":[51,94],"useful":[52],"information.":[53,75],"In":[54],"this":[55],"paper,":[56],"we":[57,111],"design":[58],"feature":[61],"enhancement":[62],"(SFE)":[63],"module":[64,116],"based":[65],"on":[66,88,132],"self-attention":[67],"mechanism":[68],"make":[70],"full":[71],"use":[72],"Moreover,":[76],"in":[77],"recent":[78],"years":[79],"temporal":[80,90,98,114,123],"convolutional":[81,115],"network":[82,129],"(TCN)":[83],"has":[84],"demonstrated":[85],"great":[86],"effect":[87],"overcomes":[93],"drawbacks":[95],"existing":[97],"information":[99],"extraction":[100],"methods":[101],"such":[102],"as":[103],"HMM,":[104],"RNN":[105],"and":[106,139],"LSTM.":[107],"Inspired":[108],"by":[109],"this,":[110],"propose":[112],"(TCM)":[117],"is":[119,130],"suitable":[120],"extract":[122],"context":[124],"music.":[126],"Our":[127],"proposed":[128],"validated":[131],"MAPS":[134],"dataset":[135],"for":[136],"transcription,":[138],"achieves":[140],"ideal":[141],"performance.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}