{"id":"https://openalex.org/W2890285072","doi":"https://doi.org/10.1109/icassp.2018.8461914","title":"Towards Complete Polyphonic Music Transcription: Integrating Multi-Pitch Detection and Rhythm Quantization","display_name":"Towards Complete Polyphonic Music Transcription: Integrating Multi-Pitch Detection and Rhythm Quantization","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890285072","doi":"https://doi.org/10.1109/icassp.2018.8461914","mag":"2890285072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/40583/1/Benetos%20Towards%20Complete%20Polyphonic%202018%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043140898","display_name":"Eita Nakamura","orcid":"https://orcid.org/0000-0003-4097-6027"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Eita Nakamura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043140898"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":4.3108,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.95310874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"105"},"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":0.9983000159263611,"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":0.9936000108718872,"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/polyphony","display_name":"Polyphony","score":0.8795210123062134},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.7193968892097473},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6880753636360168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6686803698539734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6278738975524902},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5775833129882812},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5715676546096802},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2533757984638214},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18007105588912964},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15195629000663757},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09367826581001282},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08566606044769287}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8795210123062134},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.7193968892097473},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6880753636360168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6686803698539734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6278738975524902},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5775833129882812},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5715676546096802},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2533757984638214},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18007105588912964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15195629000663757},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09367826581001282},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08566606044769287},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8461914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/40583","is_oa":true,"landing_page_url":"http://qmro.qmul.ac.uk/xmlui/handle/123456789/40583","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/40583/1/Benetos%20Towards%20Complete%20Polyphonic%202018%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/40583","is_oa":true,"landing_page_url":"http://qmro.qmul.ac.uk/xmlui/handle/123456789/40583","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/40583/1/Benetos%20Towards%20Complete%20Polyphonic%202018%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890285072.pdf","grobid_xml":"https://content.openalex.org/works/W2890285072.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W89231944","https://openalex.org/W94439923","https://openalex.org/W129413713","https://openalex.org/W2000911789","https://openalex.org/W2016503548","https://openalex.org/W2024514957","https://openalex.org/W2049633694","https://openalex.org/W2086127342","https://openalex.org/W2096482524","https://openalex.org/W2105143211","https://openalex.org/W2110007838","https://openalex.org/W2120053230","https://openalex.org/W2129433179","https://openalex.org/W2149507868","https://openalex.org/W2150319510","https://openalex.org/W2156012518","https://openalex.org/W2169784142","https://openalex.org/W2171850596","https://openalex.org/W2198584637","https://openalex.org/W2293027038","https://openalex.org/W2294404390","https://openalex.org/W2400676457","https://openalex.org/W2577545569","https://openalex.org/W2583498619","https://openalex.org/W2726158836","https://openalex.org/W2773928913","https://openalex.org/W2773935811","https://openalex.org/W2950335938","https://openalex.org/W6603626069","https://openalex.org/W6603888401","https://openalex.org/W6674508888","https://openalex.org/W6676601233","https://openalex.org/W6682952417","https://openalex.org/W6696796203","https://openalex.org/W6697316635","https://openalex.org/W6713148187","https://openalex.org/W6732146819","https://openalex.org/W6733936739","https://openalex.org/W6740474043","https://openalex.org/W6746766806","https://openalex.org/W6746767065"],"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/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2340483794","https://openalex.org/W2132597408"],"abstract_inverted_index":{"Most":[0],"work":[1],"on":[2,131],"automatic":[3],"transcription":[4,22],"produces":[5,55],"\u201cpiano":[6],"roll\u201d":[7],"data":[8,136],"with":[9],"no":[10],"musical":[11,33,74],"interpretation":[12],"of":[13,106,113,118,144],"the":[14,49,52,90,97,103,111,142],"rhythm":[15,40,80],"or":[16],"pitches.":[17],"We":[18,100],"present":[19],"a":[20,26,31,79],"polyphonic":[21],"method":[23,82],"that":[24,51,66,83,138],"converts":[25],"music":[27],"audio":[28],"signal":[29],"into":[30],"human-readable":[32],"score,":[34],"by":[35,48,88,109],"integrating":[36],"multi-pitch":[37,53,107],"detection":[38,54,108],"and":[39,62,95,116],"quantization":[41,81],"methods.":[42],"This":[43],"integration":[44],"is":[45],"made":[46],"difficult":[47],"fact":[50],"erroneous":[56],"notes":[57,61,87,115],"such":[58],"as":[59,150],"extra":[60,86],"introduces":[63],"timing":[64],"errors":[65],"are":[67],"added":[68],"to":[69,73],"temporal":[70],"deviations":[71],"due":[72],"expression.":[75],"Thus,":[76],"we":[77,122],"propose":[78,123],"can":[84,147],"remove":[85],"extending":[89],"metrical":[91],"hidden":[92],"Markov":[93],"model":[94,98],"optimize":[96],"parameters.":[99],"also":[101],"improve":[102,141],"note-tracking":[104],"process":[105],"refining":[110],"treatment":[112],"repeated":[114],"adjustment":[117],"onset":[119],"times.":[120],"Finally,":[121],"evaluation":[124],"measures":[125],"for":[126,152],"transcribed":[127],"scores.":[128],"Systematic":[129],"evaluations":[130],"commonly":[132],"used":[133,149],"classical":[134],"piano":[135],"show":[137],"these":[139],"treatments":[140],"performance":[143],"transcription,":[145],"which":[146],"be":[148],"benchmarks":[151],"further":[153],"studies.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
