{"id":"https://openalex.org/W2134387846","doi":"https://doi.org/10.1109/jstsp.2011.2159577","title":"LyricSynchronizer: Automatic Synchronization System Between Musical Audio Signals and Lyrics","display_name":"LyricSynchronizer: Automatic Synchronization System Between Musical Audio Signals and Lyrics","publication_year":2011,"publication_date":"2011-06-21","ids":{"openalex":"https://openalex.org/W2134387846","doi":"https://doi.org/10.1109/jstsp.2011.2159577","mag":"2134387846"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2011.2159577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2011.2159577","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal 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/A5110207817","display_name":"Hiromasa Fujihara","orcid":null},"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":true,"raw_author_name":"Hiromasa Fujihara","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, 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), Tsukuba, Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006504365","display_name":"Jun Ogata","orcid":null},"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":"Jun Ogata","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"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":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto University, Kyoto, Japan","Kyoto University, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110207817"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":5.9271,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.96948403,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"5","issue":"6","first_page":"1252","last_page":"1261"},"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/lyrics","display_name":"Lyrics","score":0.8922663927078247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7936804294586182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7735528349876404},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.6887966394424438},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6369227170944214},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.48331165313720703},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.446621298789978},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4351484477519989},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.43241631984710693},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42951536178588867},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.41006743907928467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.371563196182251},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22854232788085938},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19519105553627014}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8922663927078247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936804294586182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7735528349876404},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.6887966394424438},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6369227170944214},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.48331165313720703},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.446621298789978},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4351484477519989},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.43241631984710693},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42951536178588867},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.41006743907928467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.371563196182251},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22854232788085938},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19519105553627014},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/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/jstsp.2011.2159577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2011.2159577","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.2490","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.2490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.aist.go.jp/m.goto/PAPER/IEEEJSTSP201110fujihara.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W89231944","https://openalex.org/W93048866","https://openalex.org/W99956014","https://openalex.org/W165283731","https://openalex.org/W218087806","https://openalex.org/W1519655822","https://openalex.org/W1585181552","https://openalex.org/W1935171541","https://openalex.org/W2019801352","https://openalex.org/W2023800933","https://openalex.org/W2060998236","https://openalex.org/W2100969003","https://openalex.org/W2107058149","https://openalex.org/W2124867748","https://openalex.org/W2133059825","https://openalex.org/W2134096203","https://openalex.org/W2136442985","https://openalex.org/W2146871184","https://openalex.org/W2148154194","https://openalex.org/W2152591660","https://openalex.org/W2159377400","https://openalex.org/W2168103573","https://openalex.org/W2168403679","https://openalex.org/W2172046423","https://openalex.org/W2398871418","https://openalex.org/W2575678548","https://openalex.org/W6603626069","https://openalex.org/W6604047900","https://openalex.org/W6606787761","https://openalex.org/W6631117800","https://openalex.org/W6634989905","https://openalex.org/W6675746282","https://openalex.org/W6712736788"],"related_works":["https://openalex.org/W2552590214","https://openalex.org/W3207249698","https://openalex.org/W2935701729","https://openalex.org/W2290770594","https://openalex.org/W2059239154","https://openalex.org/W2156230116","https://openalex.org/W2168987487","https://openalex.org/W182406043","https://openalex.org/W2134387846","https://openalex.org/W2516392987"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,57,77,83,90,97,101],"system":[4,129],"that":[5,126],"can":[6],"automatically":[7],"synchronize":[8],"polyphonic":[9],"musical":[10],"audio":[11],"signals":[12,23],"with":[13],"their":[14],"corresponding":[15,25],"lyrics.":[16,134],"Although":[17],"methods":[18,37,72,118],"for":[19,60,79,85,92,99,114,130],"synchronizing":[20,131],"monophonic":[21],"speech":[22],"and":[24,96,119,133],"text":[26],"transcriptions":[27],"by":[28,51],"using":[29],"Viterbi":[30],"alignment":[31],"techniques":[32],"have":[33],"been":[34],"proposed,":[35],"these":[36,117],"cannot":[38],"be":[39],"applied":[40],"to":[41,56,73,105],"vocals":[42,47],"in":[43],"CD":[44],"recordings":[45],"because":[46],"are":[48],"often":[49],"overlapped":[50],"accompaniment":[52,66],"sounds.":[53],"In":[54],"addition":[55],"conventional":[58],"method":[59,78,84,91,98],"reducing":[61],"the":[62,65],"influence":[63],"of":[64,116],"sounds,":[67,95],"we":[68],"therefore":[69],"developed":[70],"four":[71],"overcome":[74],"this":[75],"problem:":[76],"detecting":[80,93],"vocal":[81,107],"sections,":[82],"constructing":[86],"robust":[87],"phoneme":[88],"networks,":[89],"fricative":[94],"adapting":[100],"speech-recognizer":[102],"phone":[103],"model":[104],"segregated":[106],"signals.":[108],"We":[109],"then":[110],"report":[111],"experimental":[112],"results":[113],"each":[115],"also":[120],"describe":[121],"our":[122,128],"music":[123,132],"playback":[124],"interface":[125],"utilizes":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
