{"id":"https://openalex.org/W2939480517","doi":"https://doi.org/10.1109/icassp.2019.8682817","title":"Joint Transcription of Lead, Bass, and Rhythm Guitars Based on a Factorial Hidden Semi-Markov Model","display_name":"Joint Transcription of Lead, Bass, and Rhythm Guitars Based on a Factorial Hidden Semi-Markov Model","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939480517","doi":"https://doi.org/10.1109/icassp.2019.8682817","mag":"2939480517"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682817","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/A5085150511","display_name":"Kentaro Shibata","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Shibata","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025832278","display_name":"Ryo Nishikimi","orcid":"https://orcid.org/0000-0002-3638-6115"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Nishikimi","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098968","display_name":"Satoru Fukayama","orcid":"https://orcid.org/0000-0001-6506-2796"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Fukayama","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eita Nakamura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"236","last_page":"240"},"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":0.9993000030517578,"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":0.9987999796867371,"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/guitar","display_name":"Guitar","score":0.8728814721107483},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7697925567626953},{"id":"https://openalex.org/keywords/bass","display_name":"Bass (fish)","score":0.734028697013855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.709844172000885},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6870629191398621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5761109590530396},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4228343963623047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40848276019096375},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2492484450340271},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.23060405254364014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12005653977394104}],"concepts":[{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.8728814721107483},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7697925567626953},{"id":"https://openalex.org/C2777182073","wikidata":"https://www.wikidata.org/wiki/Q1224135","display_name":"Bass (fish)","level":2,"score":0.734028697013855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.709844172000885},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6870629191398621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5761109590530396},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4228343963623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40848276019096375},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2492484450340271},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.23060405254364014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12005653977394104},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682817","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":42,"referenced_works":["https://openalex.org/W173783047","https://openalex.org/W1528056001","https://openalex.org/W1561135842","https://openalex.org/W1822807512","https://openalex.org/W1935284635","https://openalex.org/W1959608418","https://openalex.org/W2024514957","https://openalex.org/W2029337446","https://openalex.org/W2031696998","https://openalex.org/W2096482524","https://openalex.org/W2099471712","https://openalex.org/W2104298926","https://openalex.org/W2105143211","https://openalex.org/W2120809168","https://openalex.org/W2147834639","https://openalex.org/W2155531311","https://openalex.org/W2198584637","https://openalex.org/W2400676457","https://openalex.org/W2405656250","https://openalex.org/W2408151306","https://openalex.org/W2578153311","https://openalex.org/W2583498619","https://openalex.org/W2756044476","https://openalex.org/W2771763364","https://openalex.org/W2773294482","https://openalex.org/W2774707525","https://openalex.org/W2950693330","https://openalex.org/W4245655784","https://openalex.org/W4297809150","https://openalex.org/W4320013936","https://openalex.org/W6607058411","https://openalex.org/W6633727632","https://openalex.org/W6640379892","https://openalex.org/W6640963894","https://openalex.org/W6681822791","https://openalex.org/W6713148187","https://openalex.org/W6713612563","https://openalex.org/W6732665659","https://openalex.org/W6744199053","https://openalex.org/W6746486700","https://openalex.org/W6746836464","https://openalex.org/W6746914816"],"related_works":["https://openalex.org/W4362728500","https://openalex.org/W2769794111","https://openalex.org/W2065787233","https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2194396582","https://openalex.org/W2082284720","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2379938888"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,39,61,66,91,103,119,126,137,140,154,170],"statistical":[4],"method":[5,174],"for":[6,10,99,113],"estimating":[7],"musical":[8,40,107,123],"scores":[9],"lead,":[11],"bass,":[12],"and":[13,31,59,86,111,115,128,178],"rhythm":[14,100],"guitars":[15,117],"from":[16],"polyphonic":[17],"audio":[18],"signals":[19],"of":[20,47,56,73,90,106,122,142,145,180],"typical":[21],"band-style":[22],"music.":[23],"To":[24],"perform":[25],"multi-instrument":[26],"transcription":[27],"involving":[28],"multi-pitch":[29,172],"detection":[30,173],"part":[32,49,57],"assignment,":[33],"it":[34],"is":[35],"crucial":[36],"to":[37,52,78],"formulate":[38],"language":[41,75,97],"model":[42,70,89,98,135,168],"that":[43,71,166],"represents":[44,102,136],"the":[45,54,79,146,158,176,181],"characteristics":[46],"each":[48],"in":[50,125,175],"order":[51],"solve":[53],"ambiguity":[55],"assignment":[58],"estimate":[60,157],"musically-natural":[62],"score.":[63],"We":[64,164],"propose":[65],"factorial":[67],"hidden":[68],"semi-Markov":[69],"consists":[72],"three":[74,80,147],"models":[76],"corresponding":[77],"guitar":[81,101,148],"parts":[82,149],"(three":[83],"latent":[84],"chains)":[85],"an":[87],"acoustic":[88,134],"mixture":[92],"spectrogram":[93,138],"(emission":[94],"model).":[95],"The":[96,133],"homophonic":[104],"sequence":[105,121],"notes":[108,124],"(chord":[109],"sequence)":[110],"those":[112],"lead":[114],"bass":[116],"represent":[118],"monophonic":[120],"higher":[127],"lower":[129],"frequency":[130],"range":[131],"respectively.":[132],"as":[139],"sum":[141],"low-rank":[143],"spectrograms":[144],"approximated":[150],"by":[151],"NMF.":[152],"Given":[153],"spectrogram,":[155],"we":[156],"note":[159],"sequences":[160],"using":[161],"Gibbs":[162],"sampling.":[163],"show":[165],"our":[167],"outperforms":[169],"state-of-the-art":[171],"accuracy":[177],"naturalness":[179],"transcribed":[182],"scores.":[183]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}