{"id":"https://openalex.org/W2028766658","doi":"https://doi.org/10.1145/1823746.1823753","title":"Word level automatic alignment of music and lyrics using vocal synthesis","display_name":"Word level automatic alignment of music and lyrics using vocal synthesis","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2028766658","doi":"https://doi.org/10.1145/1823746.1823753","mag":"2028766658"},"language":"en","primary_location":{"id":"doi:10.1145/1823746.1823753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1823746.1823753","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061102347","display_name":"Namunu C. Maddage","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Namunu C. Maddage","raw_affiliation_strings":["Royal Melbourne Institute of Technology (RMIT), Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Royal Melbourne Institute of Technology (RMIT), Melbourne, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061102347"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3383,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56400813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"6","issue":"3","first_page":"1","last_page":"16"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9987999796867371,"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/lyrics","display_name":"Lyrics","score":0.9609850645065308},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9195858240127563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7591996192932129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390233278274536},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4731011390686035},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4718480110168457},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4607544541358948},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4434361457824707},{"id":"https://openalex.org/keywords/vocal-music","display_name":"Vocal music","score":0.42178812623023987},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.42067885398864746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35924232006073},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25834137201309204},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1767190396785736},{"id":"https://openalex.org/keywords/music","display_name":"Music","score":0.10195291042327881}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9609850645065308},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9195858240127563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7591996192932129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390233278274536},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4731011390686035},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4718480110168457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4607544541358948},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4434361457824707},{"id":"https://openalex.org/C553614217","wikidata":"https://www.wikidata.org/wiki/Q685884","display_name":"Vocal music","level":4,"score":0.42178812623023987},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.42067885398864746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35924232006073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25834137201309204},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1767190396785736},{"id":"https://openalex.org/C535889608","wikidata":"https://www.wikidata.org/wiki/Q638","display_name":"Music","level":3,"score":0.10195291042327881},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C13553968","wikidata":"https://www.wikidata.org/wiki/Q27908","display_name":"Music education","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1823746.1823753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1823746.1823753","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:12971","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:12971","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:alma.61RMIT_INST:11246409380001341","is_oa":false,"landing_page_url":"http://doi.org/10.1145/1823746.1823753","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27438471","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27438471","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W99956014","https://openalex.org/W355080943","https://openalex.org/W943204654","https://openalex.org/W1482650115","https://openalex.org/W1492190885","https://openalex.org/W1493163583","https://openalex.org/W1496437476","https://openalex.org/W1503560067","https://openalex.org/W1510737763","https://openalex.org/W1521585602","https://openalex.org/W1537357046","https://openalex.org/W1560013842","https://openalex.org/W1585181552","https://openalex.org/W1865819098","https://openalex.org/W1878590289","https://openalex.org/W1966264494","https://openalex.org/W1979188593","https://openalex.org/W1989859754","https://openalex.org/W2042105302","https://openalex.org/W2042487788","https://openalex.org/W2060998236","https://openalex.org/W2088867696","https://openalex.org/W2095282534","https://openalex.org/W2103869314","https://openalex.org/W2105095599","https://openalex.org/W2124867748","https://openalex.org/W2128117472","https://openalex.org/W2128160875","https://openalex.org/W2134096203","https://openalex.org/W2153331925","https://openalex.org/W2154473523","https://openalex.org/W2164282073","https://openalex.org/W2174404816","https://openalex.org/W2396871547","https://openalex.org/W2603415636","https://openalex.org/W6632355583"],"related_works":["https://openalex.org/W2378183644","https://openalex.org/W2287414930","https://openalex.org/W2376225760","https://openalex.org/W2389730807","https://openalex.org/W3113285152","https://openalex.org/W2347722545","https://openalex.org/W2367547137","https://openalex.org/W2393107058","https://openalex.org/W2383688572","https://openalex.org/W2387240545"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,29,121],"signal-based":[3],"approach":[4,144],"instead":[5],"of":[6,56,65,104,115],"the":[7,21,34,39,45,49,54,63,109],"commonly":[8],"used":[9],"model-based":[10],"approach,":[11,26],"to":[12,32,38,107,151],"automatically":[13],"align":[14],"vocal":[15,111],"music":[16,46,66,74,80,84,86,105],"with":[17,48],"text":[18,51],"lyrics":[19,52],"at":[20,133],"word":[22,128],"level.":[23],"In":[24,41,73],"this":[25,42],"we":[27,77,97],"use":[28,103],"text-to-speech":[30],"system":[31],"synthesize":[33],"singing":[35,70,94,99],"voice":[36,71,95,100],"according":[37],"lyrics.":[40],"way,":[43],"aligning":[44],"signal":[47],"corresponding":[50],"becomes":[53],"alignment":[55,130,139,153],"two":[57],"audio":[58],"signals.":[59],"This":[60],"study":[61,78],"uses":[62],"results":[64,119],"information":[67,75],"modeling":[68],"and":[69,89,126,136,148],"synthesis.":[72],"modeling,":[76],"different":[79],"representation":[81],"strategies":[82],"for":[83],"segmentation,":[85],"region":[87,90],"indexing":[88],"content":[91],"descriptions;":[92],"in":[93,113],"synthesis,":[96],"generate":[98],"by":[101],"making":[102],"knowledge":[106],"approximate":[108],"target":[110],"line":[112],"terms":[114],"tempo.":[116],"The":[117,142],"experimental":[118],"on":[120],"20-song":[122],"database":[123],"show":[124],"26.3%":[125],"36.1%":[127],"level":[129],"error":[131],"rates":[132],"eighth":[134],"note":[135,138],"sixteenth":[137],"tolerances":[140],"respectively.":[141],"proposed":[143],"presents":[145],"an":[146],"alternative":[147],"effective":[149],"solution":[150],"music-lyrics":[152],"which":[154],"may":[155],"require":[156],"less":[157],"training":[158],"dataset.":[159]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
