{"id":"https://openalex.org/W2939988664","doi":"https://doi.org/10.1109/icassp.2019.8682605","title":"Polyphonic Music Transcription with Semantic Segmentation","display_name":"Polyphonic Music Transcription with Semantic Segmentation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939988664","doi":"https://doi.org/10.1109/icassp.2019.8682605","mag":"2939988664"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taiwan Normal University, Taipei, 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, National Taiwan Normal University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Taiwan Normal University, Taipei, 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":null,"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":4.0142,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95222321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"170"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9968000054359436,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9955999851226807,"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":0.7653999328613281},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7247418761253357},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.709524929523468},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6647568941116333},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6183634996414185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5731105804443359},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4767609238624573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4595237672328949},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3344092071056366},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32213500142097473},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09511938691139221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653999328613281},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7247418761253357},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.709524929523468},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6647568941116333},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6183634996414185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5731105804443359},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4767609238624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4595237672328949},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3344092071056366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32213500142097473},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09511938691139221},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2001426554","https://openalex.org/W2105343238","https://openalex.org/W2110007838","https://openalex.org/W2120340098","https://openalex.org/W2149180301","https://openalex.org/W2575864022","https://openalex.org/W2630837129","https://openalex.org/W2773294482","https://openalex.org/W2774707525","https://openalex.org/W2891814570","https://openalex.org/W2891901715","https://openalex.org/W2898148140","https://openalex.org/W2902480954","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2963045359","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963551352","https://openalex.org/W2964309882","https://openalex.org/W4289563769","https://openalex.org/W4293775315","https://openalex.org/W6639824700","https://openalex.org/W6731597384","https://openalex.org/W6733936739","https://openalex.org/W6739696289","https://openalex.org/W6745851314","https://openalex.org/W6746836464","https://openalex.org/W6746914816","https://openalex.org/W6754881664","https://openalex.org/W6755182157","https://openalex.org/W6756648248"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2340483794","https://openalex.org/W2132597408","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"The":[0,63],"multi-instrument":[1,85],"transcription":[2,64],"task":[3,65],"refers":[4],"to":[5,37,50],"joint":[6],"recognition":[7],"of":[8,12,25,59,90],"instrument":[9,78],"and":[10,56,77,84],"pitch":[11,57,61,74],"every":[13],"event":[14],"in":[15],"polyphonic":[16],"music":[17,26],"signals":[18],"generated":[19],"by":[20],"one":[21],"or":[22],"more":[23],"classes":[24],"instruments.":[27],"In":[28],"this":[29,39],"paper,":[30],"we":[31],"leverage":[32],"multi-object":[33],"semantic":[34],"segmentation":[35],"techniques":[36],"solve":[38],"problem.":[40],"We":[41],"design":[42],"a":[43,60,68],"time-frequency":[44],"representation,":[45],"which":[46],"has":[47],"multiple":[48],"channels":[49],"jointly":[51],"represent":[52],"the":[53,88,91],"harmonic":[54],"structure":[55],"saliency":[58],"activation.":[62],"therefore":[66],"becomes":[67],"pixel-wise":[69],"multi-task":[70],"classification":[71],"problem":[72],"including":[73],"activity":[75],"detection":[76],"recognition.":[79],"Experiments":[80],"on":[81],"both":[82],"single-":[83],"data":[86],"verify":[87],"competitiveness":[89],"proposed":[92],"method.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
