{"id":"https://openalex.org/W4392903104","doi":"https://doi.org/10.1109/icassp48485.2024.10445926","title":"A Real-Time Lyrics Alignment System Using Chroma and Phonetic Features for Classical Vocal Performance","display_name":"A Real-Time Lyrics Alignment System Using Chroma and Phonetic Features for Classical Vocal Performance","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903104","doi":"https://doi.org/10.1109/icassp48485.2024.10445926"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445926","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5034257985","display_name":"Jiyun Park","orcid":"https://orcid.org/0000-0001-6105-0691"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jiyun Park","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,South Korea","Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014282591","display_name":"Sangeon Yong","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangeon Yong","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,South Korea","Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115444778","display_name":"Taegyun Kwon","orcid":"https://orcid.org/0009-0004-8510-872X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taegyun Kwon","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,South Korea","Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,South Korea","Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034257985"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02843069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"92","issue":null,"first_page":"1371","last_page":"1375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9918000102043152,"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/lyrics","display_name":"Lyrics","score":0.9732353687286377},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8243550658226013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806863188743591},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6575078964233398},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5496653914451599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297091066837311},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.4126484990119934},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13011673092842102}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9732353687286377},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8243550658226013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806863188743591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6575078964233398},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5496653914451599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297091066837311},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.4126484990119934},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13011673092842102},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445926","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W93815243","https://openalex.org/W2033918847","https://openalex.org/W2074417845","https://openalex.org/W2077804127","https://openalex.org/W2144234122","https://openalex.org/W2150452896","https://openalex.org/W2340080546","https://openalex.org/W2396777931","https://openalex.org/W2609300858","https://openalex.org/W2891198685","https://openalex.org/W2900749583","https://openalex.org/W2917340025","https://openalex.org/W2935701729","https://openalex.org/W3015315843","https://openalex.org/W3127686677","https://openalex.org/W3162528130","https://openalex.org/W3163088658","https://openalex.org/W3197905771","https://openalex.org/W4224931246","https://openalex.org/W4372260429","https://openalex.org/W4372349499","https://openalex.org/W6603836127","https://openalex.org/W6607858583","https://openalex.org/W6608238415","https://openalex.org/W6697077905","https://openalex.org/W6712505711","https://openalex.org/W6732426729","https://openalex.org/W6733936739","https://openalex.org/W6757122045","https://openalex.org/W6786603260","https://openalex.org/W6799375923"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W2118466154","https://openalex.org/W2597614303","https://openalex.org/W634160686","https://openalex.org/W4310670065","https://openalex.org/W1984378309","https://openalex.org/W2413768264","https://openalex.org/W2378183644","https://openalex.org/W2363573956","https://openalex.org/W2287414930"],"abstract_inverted_index":{"The":[0,26],"goal":[1],"of":[2,37,55,71,92,123,135,153],"real-time":[3,45,74,100,163],"lyrics":[4,22,77,101,115,164],"alignment":[5,102,116],"is":[6],"to":[7,15,52,68],"take":[8],"live":[9,38],"singing":[10,137],"audio":[11],"as":[12,33,157],"input":[13,59],"and":[14,60,125,132],"pinpoint":[16],"the":[17,24,34,53,69,114,136,143,154,162],"exact":[18],"position":[19],"within":[20,62],"given":[21],"on":[23],"fly.":[25],"task":[27],"can":[28],"benefit":[29],"real-world":[30],"applications":[31],"such":[32],"automatic":[35],"subtitling":[36],"concerts":[39],"or":[40],"operas.":[41],"However,":[42],"designing":[43],"a":[44,48,63,90,99],"model":[46],"poses":[47],"great":[49],"challenge":[50],"due":[51,67],"constraints":[54],"only":[56],"using":[57],"past":[58],"operating":[61],"minimal":[64],"latency.":[65],"Furthermore,":[66],"lack":[70,91],"datasets":[72],"for":[73,76,104,161],"models":[75],"alignment,":[78],"previous":[79],"studies":[80],"have":[81],"mostly":[82],"evaluated":[83],"with":[84,108],"private":[85],"in-house":[86],"datasets,":[87],"resulting":[88],"in":[89],"standard":[93],"evaluation":[94,159],"methods.":[95],"This":[96],"paper":[97],"presents":[98],"system":[103],"classical":[105],"vocal":[106],"performances":[107],"two":[109],"contributions.":[110],"First,":[111],"we":[112,141],"improve":[113],"algorithm":[117],"by":[118],"finding":[119],"an":[120,158],"optimal":[121],"combination":[122],"chromagram":[124],"phonetic":[126],"posteriorgram":[127],"(PPG)":[128],"that":[129],"capture":[130],"melodic":[131],"phonetics":[133],"features":[134],"voice,":[138],"respectively.":[139],"Second,":[140],"recast":[142],"Schubert":[144],"Winterreise":[145],"Dataset":[146],"(SWD)":[147],"which":[148],"contains":[149],"multiple":[150],"performance":[151],"renditions":[152],"same":[155],"pieces":[156],"set":[160],"alignment.":[165]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}