{"id":"https://openalex.org/W2482558056","doi":"https://doi.org/10.1109/taslp.2016.2594282","title":"Alignment of Lyrics With Accompanied Singing Audio Based on Acoustic-Phonetic Vowel Likelihood Modeling","display_name":"Alignment of Lyrics With Accompanied Singing Audio Based on Acoustic-Phonetic Vowel Likelihood Modeling","publication_year":2016,"publication_date":"2016-07-27","ids":{"openalex":"https://openalex.org/W2482558056","doi":"https://doi.org/10.1109/taslp.2016.2594282","mag":"2482558056"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2594282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2594282","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5008038664","display_name":"Yu-Ren Chien","orcid":"https://orcid.org/0000-0002-2104-3814"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"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":true,"raw_author_name":"Yu-Ren Chien","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taipei, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"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":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028285867","display_name":"Shyh\u2010Kang Jeng","orcid":"https://orcid.org/0000-0001-8960-9995"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shyh-Kang Jeng","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008038664"],"corresponding_institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":2.2696,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89002025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"24","issue":"11","first_page":"1998","last_page":"2008"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9993000030517578,"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/formant","display_name":"Formant","score":0.8363645076751709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7065010070800781},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.695820689201355},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.6923589110374451},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6638157963752747},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.6385955810546875},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5284357666969299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5241482257843018},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.42660266160964966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3699952960014343}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8363645076751709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7065010070800781},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.695820689201355},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.6923589110374451},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6638157963752747},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.6385955810546875},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5284357666969299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5241482257843018},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42660266160964966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3699952960014343},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2594282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2594282","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5834725963","display_name":null,"funder_award_id":"102-2221-E-001-008-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W67840865","https://openalex.org/W83475003","https://openalex.org/W93276847","https://openalex.org/W573069471","https://openalex.org/W1496589961","https://openalex.org/W1558306184","https://openalex.org/W1838578708","https://openalex.org/W1875892135","https://openalex.org/W2001719495","https://openalex.org/W2022194925","https://openalex.org/W2052675777","https://openalex.org/W2057745663","https://openalex.org/W2060998236","https://openalex.org/W2088867696","https://openalex.org/W2088959886","https://openalex.org/W2089170860","https://openalex.org/W2114352222","https://openalex.org/W2125838338","https://openalex.org/W2134387846","https://openalex.org/W2144827818","https://openalex.org/W2164336224","https://openalex.org/W2166209411","https://openalex.org/W2343253662","https://openalex.org/W6602696525","https://openalex.org/W6603486410","https://openalex.org/W6603815646","https://openalex.org/W6629505628","https://openalex.org/W6639128508"],"related_works":["https://openalex.org/W2001832747","https://openalex.org/W2028715205","https://openalex.org/W2344358524","https://openalex.org/W2060888333","https://openalex.org/W2053092242","https://openalex.org/W2028342517","https://openalex.org/W3042758298","https://openalex.org/W2050311283","https://openalex.org/W2942435052","https://openalex.org/W3169184738"],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,83,97,104,159],"task":[4],"of":[5,16,24,39,55,64,106,109,141],"aligning":[6],"lyrics":[7,68],"with":[8,27,51,138],"accompanied":[9],"singing":[10,40],"recordings.":[11],"With":[12],"a":[13,36,52,119,125,139,148],"vowel-only":[14],"representation":[15],"lyric":[17],"syllables,":[18],"our":[19],"approach":[20],"evaluates":[21],"likelihood":[22,45],"scores":[23],"vowel":[25,44],"types":[26],"glottal":[28,110,144],"pulse":[29,111,145],"shapes":[30,112],"and":[31,80,113],"formant":[32,114],"frequencies":[33,115],"extracted":[34],"from":[35],"small":[37],"set":[38],"examples.":[41],"The":[42],"proposed":[43],"model":[46,54],"is":[47,116],"used":[48],"in":[49,59,96,128],"conjunction":[50],"prior":[53],"frame-wise":[56],"syllable":[57],"sequence":[58],"determining":[60],"an":[61],"optimal":[62],"evolution":[63],"syllabic":[65],"position.":[66],"In":[67],"alignment":[69,131,152],"experiments,":[70],"we":[71],"optimized":[72,84],"numerical":[73],"parameters":[74],"on":[75,86],"two":[76,87],"independent":[77],"development":[78],"sets":[79],"then":[81],"tested":[82],"system":[85],"other":[88],"datasets.":[89],"New":[90],"objective":[91],"performance":[92],"measures":[93],"are":[94],"introduced":[95],"evaluation":[98],"to":[99,122],"provide":[100],"further":[101],"insight":[102],"into":[103],"quality":[105],"alignment.":[107],"Use":[108],"shown":[117],"by":[118,163],"controlled":[120,134],"experiment":[121,135],"account":[123],"for":[124],"0.07":[126],"difference":[127,140],"average":[129,150],"normalized":[130,151],"error.":[132],"Another":[133],"demonstrates":[136],"that,":[137],"0.03,":[142],"F0-invariant":[143,156],"shape":[146],"gives":[147],"lower":[149],"error":[153],"than":[154],"does":[155],"spectrum":[157],"envelope,":[158],"latter":[160],"being":[161],"assumed":[162],"MFCC-based":[164],"timbre":[165],"models.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
