{"id":"https://openalex.org/W2607858038","doi":"https://doi.org/10.1587/transinf.2016edp7387","title":"Robust Singing Transcription System Using Local Homogeneity in the Harmonic Structure","display_name":"Robust Singing Transcription System Using Local Homogeneity in the Harmonic Structure","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2607858038","doi":"https://doi.org/10.1587/transinf.2016edp7387","mag":"2607858038"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016edp7387","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7387","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7387/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7387/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077537780","display_name":"Hoon Heo","orcid":"https://orcid.org/0009-0007-9779-6429"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210147194","display_name":"Convergence","ror":"https://ror.org/03kcznq08","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210147194"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Hoon HEO","raw_affiliation_strings":["Music and Audio Research Group, Graduate School of Convergence Science and Technology, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group, Graduate School of Convergence Science and Technology, Seoul National University","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210147194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210120602","display_name":"Advanced Institute of Convergence Technology","ror":"https://ror.org/01w62yz22","country_code":"KR","type":"facility","lineage":["https://openalex.org/I139264467","https://openalex.org/I4210120602"]},{"id":"https://openalex.org/I4210147194","display_name":"Convergence","ror":"https://ror.org/03kcznq08","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210147194"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Kyogu LEE","raw_affiliation_strings":["Advanced Institutes of Convergence Technology","Music and Audio Research Group, Graduate School of Convergence Science and Technology, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Institutes of Convergence Technology","institution_ids":["https://openalex.org/I4210120602"]},{"raw_affiliation_string":"Music and Audio Research Group, Graduate School of Convergence Science and Technology, Seoul National University","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210147194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1868,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42384332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"E100.D","issue":"5","first_page":"1114","last_page":"1123"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7753274440765381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.64528888463974},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5960244536399841},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.573348343372345},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5506585836410522},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5325920581817627},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49711111187934875},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4778851270675659},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.4400791525840759},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4369505047798157},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.43184694647789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3900310695171356},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3849150836467743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3804430663585663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14342209696769714},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14094826579093933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753274440765381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.64528888463974},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5960244536399841},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.573348343372345},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5506585836410522},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5325920581817627},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49711111187934875},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4778851270675659},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.4400791525840759},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4369505047798157},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43184694647789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3900310695171356},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3849150836467743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3804430663585663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14342209696769714},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14094826579093933},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016edp7387","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7387","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7387/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2016edp7387","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016edp7387","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/5/E100.D_2016EDP7387/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2607858038.pdf","grobid_xml":"https://content.openalex.org/works/W2607858038.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W102255675","https://openalex.org/W1508603446","https://openalex.org/W1778811406","https://openalex.org/W1976069042","https://openalex.org/W1990908299","https://openalex.org/W2008765103","https://openalex.org/W2029337446","https://openalex.org/W2091425152","https://openalex.org/W2101722322","https://openalex.org/W2118774185","https://openalex.org/W2124120139","https://openalex.org/W2124539664","https://openalex.org/W2140304104","https://openalex.org/W2145001205","https://openalex.org/W2145905122","https://openalex.org/W2152151492","https://openalex.org/W2164973920","https://openalex.org/W2168249484","https://openalex.org/W2169790300","https://openalex.org/W2288847132","https://openalex.org/W2293137601","https://openalex.org/W2294039222","https://openalex.org/W2586947700"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2970176078","https://openalex.org/W1975359510","https://openalex.org/W2098934641","https://openalex.org/W4387698063","https://openalex.org/W2371215329","https://openalex.org/W1526651343"],"abstract_inverted_index":{"Automatic":[0],"music":[1,21],"transcription":[2,51],"from":[3,168],"audio":[4],"has":[5],"long":[6],"been":[7],"one":[8],"of":[9,20,29,68,88,121,176],"the":[10,18,69,80,89,105,111,114,127,130,134,143,154,158,173,177,184,195,203],"most":[11],"intriguing":[12],"problems":[13],"and":[14,36,91,146,162,180],"a":[15,27,49,65,72,99,119],"challenge":[16],"in":[17,83,133],"field":[19],"information":[22],"retrieval,":[23],"because":[24],"it":[25],"requires":[26],"series":[28],"low-level":[30],"tasks":[31],"such":[32],"as":[33],"onset/offset":[34],"detection":[35],"F0":[37],"estimation,":[38],"followed":[39],"by":[40,139],"high-level":[41],"post-processing":[42],"for":[43,53,188],"symbolic":[44],"representation.":[45],"In":[46],"this":[47],"paper,":[48],"comprehensive":[50],"system":[52,152,179,197],"monophonic":[54],"singing":[55,84,189],"voice":[56,85],"based":[57,103],"on":[58,104],"harmonic":[59,81,116,135],"structure":[60,82,136],"analysis":[61,145],"is":[62,76,94,137],"proposed.":[63],"Given":[64],"precise":[66],"tracking":[67],"fundamental":[70],"frequency,":[71],"novel":[73],"acoustic":[74],"feature":[75],"derived":[77],"to":[78,97,171],"signify":[79],"signals,":[86],"regardless":[87],"loudness":[90],"pitch.":[92,164],"It":[93],"then":[95],"used":[96],"generate":[98],"parametric":[100],"mixture":[101],"model":[102,112],"von":[106],"Mises-Fisher":[107],"distribution,":[108],"so":[109],"that":[110,194],"represents":[113],"intrinsic":[115],"structures":[117],"within":[118],"region":[120],"smoothly":[122],"connected":[123],"notes.":[124],"To":[125],"identify":[126],"note":[128,155,163],"boundaries,":[129],"local":[131],"homogeneity":[132],"exploited":[138],"two":[140],"different":[141],"methods:":[142],"self-similarity":[144],"hidden":[147],"Markov":[148],"model.":[149],"The":[150,191],"proposed":[151,178,196],"identifies":[153],"attributes":[156],"including":[157,202],"onset":[159],"time,":[160],"duration":[161],"Evaluations":[165],"are":[166],"conducted":[167],"various":[169],"aspects":[170],"verify":[172],"performance":[174],"improvement":[175],"its":[181],"robustness,":[182],"using":[183],"latest":[185],"evaluation":[186],"methodology":[187],"transcription.":[190],"results":[192],"show":[193],"significantly":[198],"outperforms":[199],"other":[200],"systems":[201],"state-of-the-art":[204],"systems.":[205]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
