{"id":"https://openalex.org/W3095303521","doi":"https://doi.org/10.1109/taslp.2020.3030482","title":"Multi-Instrument Automatic Music Transcription With Self-Attention-Based Instance Segmentation","display_name":"Multi-Instrument Automatic Music Transcription With Self-Attention-Based Instance Segmentation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3095303521","doi":"https://doi.org/10.1109/taslp.2020.3030482","mag":"3095303521"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3030482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030482","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/A5080942813","display_name":"Yu\u2010Te Wu","orcid":"https://orcid.org/0000-0002-6942-0340"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Te Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiepi, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiepi, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595070","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiepi, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taiepi, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4275-8832","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0346,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94543147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"2796","last_page":"2809"},"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":0.9979000091552734,"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7435330152511597},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6483628749847412},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5839509963989258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5507857799530029},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5031670928001404},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4749372601509094},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44464200735092163},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.42689594626426697},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4128059148788452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37771371006965637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36955857276916504},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3604433238506317},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25263842940330505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08978161215782166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435330152511597},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6483628749847412},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5839509963989258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507857799530029},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5031670928001404},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4749372601509094},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44464200735092163},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.42689594626426697},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4128059148788452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37771371006965637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36955857276916504},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3604433238506317},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25263842940330505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08978161215782166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3030482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030482","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":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W196347269","https://openalex.org/W1590102137","https://openalex.org/W1607142029","https://openalex.org/W1752772649","https://openalex.org/W1822807512","https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1981374696","https://openalex.org/W2001426554","https://openalex.org/W2005787925","https://openalex.org/W2017416504","https://openalex.org/W2017578549","https://openalex.org/W2065495703","https://openalex.org/W2088761115","https://openalex.org/W2095401277","https://openalex.org/W2096482524","https://openalex.org/W2105143211","https://openalex.org/W2105343238","https://openalex.org/W2107328928","https://openalex.org/W2109770219","https://openalex.org/W2110007838","https://openalex.org/W2120809168","https://openalex.org/W2125722442","https://openalex.org/W2133240958","https://openalex.org/W2139878068","https://openalex.org/W2149180301","https://openalex.org/W2183341477","https://openalex.org/W2296724634","https://openalex.org/W2407685581","https://openalex.org/W2410860376","https://openalex.org/W2523056285","https://openalex.org/W2559688696","https://openalex.org/W2575864022","https://openalex.org/W2577545569","https://openalex.org/W2593836007","https://openalex.org/W2620021285","https://openalex.org/W2630837129","https://openalex.org/W2669853845","https://openalex.org/W2747756448","https://openalex.org/W2753709519","https://openalex.org/W2759171953","https://openalex.org/W2773294482","https://openalex.org/W2774581901","https://openalex.org/W2774707525","https://openalex.org/W2885570506","https://openalex.org/W2891814570","https://openalex.org/W2898148140","https://openalex.org/W2899260162","https://openalex.org/W2902480954","https://openalex.org/W2903137797","https://openalex.org/W2903539539","https://openalex.org/W2906214917","https://openalex.org/W2913077944","https://openalex.org/W2919624000","https://openalex.org/W2939957001","https://openalex.org/W2939988664","https://openalex.org/W2948210185","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2953406194","https://openalex.org/W2963045359","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W2963493667","https://openalex.org/W2963551352","https://openalex.org/W2970206392","https://openalex.org/W2986842658","https://openalex.org/W2998490864","https://openalex.org/W3011176162","https://openalex.org/W3098670224","https://openalex.org/W3101943858","https://openalex.org/W3124061379","https://openalex.org/W4293775315","https://openalex.org/W4385245566","https://openalex.org/W6607961521","https://openalex.org/W6635274319","https://openalex.org/W6636203886","https://openalex.org/W6697040288","https://openalex.org/W6714030504","https://openalex.org/W6730401039","https://openalex.org/W6732146819","https://openalex.org/W6733936739","https://openalex.org/W6739696289","https://openalex.org/W6739901393","https://openalex.org/W6745851314","https://openalex.org/W6746836464","https://openalex.org/W6746914816","https://openalex.org/W6746960179","https://openalex.org/W6753544557","https://openalex.org/W6755182157","https://openalex.org/W6756597712","https://openalex.org/W6756648248","https://openalex.org/W6756873980","https://openalex.org/W6760601182","https://openalex.org/W6763509872","https://openalex.org/W6764722873","https://openalex.org/W6769896225"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W4230611425","https://openalex.org/W2731899572","https://openalex.org/W4304166257","https://openalex.org/W4294635752","https://openalex.org/W4383066092","https://openalex.org/W3215138031","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Multi-instrument":[0],"automatic":[1],"music":[2,16,36],"transcription":[3],"(AMT)":[4],"is":[5,92,115],"a":[6,46,59,105],"critical":[7],"but":[8],"less":[9],"investigated":[10,111],"problem":[11,48],"in":[12,86,98,118],"the":[13,22,96,119],"field":[14],"of":[15,121],"information":[17],"retrieval":[18],"(MIR).":[19],"With":[20],"all":[21,95],"difficulties":[23],"faced":[24],"by":[25,78],"traditional":[26],"AMT":[27,30,61],"research,":[28],"multi-instrument":[29,60,99,102],"needs":[31],"further":[32],"investigation":[33],"on":[34],"high-level":[35],"semantic":[37],"modeling,":[38],"efficient":[39],"training":[40],"methods":[41],"for":[42,50,94],"multiple":[43],"attributes,":[44],"and":[45,74,83],"clear":[47],"scenario":[49],"system":[51],"performance":[52,114],"evaluation.":[53],"In":[54],"this":[55],"article,":[56],"we":[57],"propose":[58],"method,":[62],"with":[63],"signal":[64],"processing":[65],"techniques":[66],"specifying":[67],"pitch":[68],"saliency,":[69],"novel":[70],"deep":[71],"learning":[72],"techniques,":[73],"concepts":[75],"partly":[76],"inspired":[77],"multi-object":[79],"recognition,":[80],"instance":[81],"segmentation,":[82],"image-to-image":[84],"translation":[85],"computer":[87],"vision.":[88],"The":[89],"proposed":[90],"method":[91],"flexible":[93],"sub-tasks":[97],"AMT,":[100],"including":[101],"note":[103],"tracking,":[104],"task":[106],"that":[107],"has":[108],"rarely":[109],"been":[110],"before.":[112],"State-of-the-art":[113],"also":[116],"reported":[117],"sub-task":[120],"multi-pitch":[122],"streaming.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}