{"id":"https://openalex.org/W2935701729","doi":"https://doi.org/10.1109/icassp.2019.8682582","title":"Automatic Lyrics-to-audio Alignment on Polyphonic Music Using Singing-adapted Acoustic Models","display_name":"Automatic Lyrics-to-audio Alignment on Polyphonic Music Using Singing-adapted Acoustic Models","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2935701729","doi":"https://doi.org/10.1109/icassp.2019.8682582","mag":"2935701729"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682582","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/A5067433878","display_name":"Bidisha Sharma","orcid":"https://orcid.org/0000-0002-4195-3532"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bidisha Sharma","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016367573","display_name":"Chitralekha Gupta","orcid":"https://orcid.org/0000-0003-1350-9095"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chitralekha Gupta","raw_affiliation_strings":["NUS Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUS Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["NUS Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUS Graduate School for Integrative Sciences and Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":3.4407,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93706205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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":0.9993000030517578,"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/lyrics","display_name":"Lyrics","score":0.9205435514450073},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9009515643119812},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.8319064378738403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.764397144317627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7630512118339539},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5600352883338928},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2641058564186096}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9205435514450073},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9009515643119812},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8319064378738403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.764397144317627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630512118339539},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5600352883338928},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2641058564186096},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682582","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":[{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W83475003","https://openalex.org/W1164175658","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1561135842","https://openalex.org/W1903029394","https://openalex.org/W2052675777","https://openalex.org/W2057745663","https://openalex.org/W2134096203","https://openalex.org/W2134387846","https://openalex.org/W2144827818","https://openalex.org/W2160815625","https://openalex.org/W2164282073","https://openalex.org/W2191779130","https://openalex.org/W2577008904","https://openalex.org/W2587994092","https://openalex.org/W2736648940","https://openalex.org/W2769075302","https://openalex.org/W2774707525","https://openalex.org/W2889429804","https://openalex.org/W2902351815","https://openalex.org/W4235128394","https://openalex.org/W6603486410","https://openalex.org/W6627665034","https://openalex.org/W6631362777","https://openalex.org/W6633727632","https://openalex.org/W6663803371","https://openalex.org/W6732426729","https://openalex.org/W6741568435","https://openalex.org/W6745913901","https://openalex.org/W6746914816","https://openalex.org/W6756588447"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W2597614303","https://openalex.org/W634160686","https://openalex.org/W2411659965","https://openalex.org/W4310670065","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W2387677326","https://openalex.org/W2378183644","https://openalex.org/W2287414930"],"abstract_inverted_index":{"Lyrics-to-audio":[0],"alignment":[1,18,79,98,133,155],"is":[2,149,158],"to":[3,31,65],"automatically":[4],"align":[5],"the":[6,10,33,46,68,78,85,94,108,114,125,132,136,152],"lyrical":[7],"words":[8],"with":[9,22,107,151],"mixed":[11],"singing":[12,42,89],"audio":[13,117],"(singing":[14],"voice+musical":[15],"accompaniment).":[16],"Such":[17],"can":[19],"be":[20],"achieved":[21],"an":[23],"automatic":[24],"speech":[25,38],"recognition":[26],"(ASR)":[27],"system.":[28],"We":[29,111,138],"propose":[30],"adapt":[32],"acoustic":[34],"model":[35],"of":[36,48,87,96,116,124,145],"a":[37,50,57,128,140,161],"recognizer":[39],"towards":[40],"solo":[41],"voice.":[43],"This":[44],"avoids":[45],"hurdles":[47],"annotating":[49],"large":[51,162],"polyphonic":[52,81,100,163],"music":[53,164],"training":[54],"dataset.":[55],"Moreover,":[56],"lexicon-modification":[58],"based":[59],"duration":[60,70],"modelling":[61],"has":[62,127],"been":[63],"incorporated":[64],"account":[66],"for":[67],"long":[69],"vowels":[71],"in":[72,93,99],"singing.":[73],"As":[74],"practical":[75],"application":[76],"demand":[77],"on":[80,131,160],"music,":[82],"we":[83],"study":[84],"effect":[86],"different":[88],"vocal":[90],"separation":[91,119],"methods":[92],"task":[95],"lyrics-to-audio":[97,154],"music.":[101],"The":[102],"extracted":[103],"vocals":[104],"are":[105],"forced-aligned":[106],"singing-adapted":[109],"models.":[110],"demonstrate":[112],"that":[113,157],"use":[115],"source":[118],"method":[120],"and":[121],"effective":[122],"end-pointing":[123],"songs":[126],"high":[129],"impact":[130],"performance":[134],"through":[135],"experiments.":[137],"report":[139],"mean":[141],"average":[142],"absolute":[143],"error":[144],"3.87":[146],"seconds,":[147],"which":[148],"comparable":[150],"state-of-the-art":[153],"system":[156],"trained":[159],"database.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}