{"id":"https://openalex.org/W2057745663","doi":"https://doi.org/10.1155/2010/546047","title":"Automatic Recognition of Lyrics in Singing","display_name":"Automatic Recognition of Lyrics in Singing","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2057745663","doi":"https://doi.org/10.1155/2010/546047","mag":"2057745663"},"language":"en","primary_location":{"id":"doi:10.1155/2010/546047","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2010/546047","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1155/2010/546047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"affiliations":[{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"affiliations":[{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079981416"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":6.8449,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.97376819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2010","issue":null,"first_page":"1","last_page":"11"},"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":0.9976999759674072,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.956636369228363},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9116589426994324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5656439065933228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40374132990837097},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.3585754632949829},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.3378176689147949},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25798773765563965},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.14160454273223877},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1044650673866272},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.04273289442062378}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.956636369228363},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9116589426994324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5656439065933228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40374132990837097},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3585754632949829},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3378176689147949},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25798773765563965},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.14160454273223877},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1044650673866272},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04273289442062378}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2010/546047","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2010/546047","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f12741002b684b00b2d93b6d8a516561","is_oa":true,"landing_page_url":"https://doaj.org/article/f12741002b684b00b2d93b6d8a516561","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2010 (2010)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2010/546047","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2010/546047","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W85840116","https://openalex.org/W153815065","https://openalex.org/W182406043","https://openalex.org/W182831726","https://openalex.org/W1558543783","https://openalex.org/W1560013842","https://openalex.org/W1579838312","https://openalex.org/W2002342963","https://openalex.org/W2007431733","https://openalex.org/W2009955221","https://openalex.org/W2050693797","https://openalex.org/W2059443479","https://openalex.org/W2060998236","https://openalex.org/W2104924374","https://openalex.org/W2111935391","https://openalex.org/W2116241760","https://openalex.org/W2122028591","https://openalex.org/W2133824856","https://openalex.org/W2144731719","https://openalex.org/W2146871184","https://openalex.org/W2150415460","https://openalex.org/W2156063339","https://openalex.org/W2158880150","https://openalex.org/W2164282073","https://openalex.org/W2164336224","https://openalex.org/W2168403679","https://openalex.org/W2169878657","https://openalex.org/W2394955069","https://openalex.org/W2398871418","https://openalex.org/W2403272360","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2935909890","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W2378183644","https://openalex.org/W2287414930"],"abstract_inverted_index":{"The":[0,22,108,119,136],"paper":[1],"considers":[2],"the":[3,43,50,56,115,165,174,176,181],"task":[4],"of":[5,52,129,153,173],"recognizing":[6],"phonemes":[7],"and":[8,30,62,103],"words":[9,167],"from":[10,45],"a":[11,16,127],"singing":[12,29,31,44,54,70,75],"input":[13],"by":[14,82,94],"using":[15,60],"phonetic":[17,96],"hidden":[18],"Markov":[19],"model":[20,123],"recognizer.":[21],"system":[23],"is":[24,39,58,71,80,124,138,168,180],"targeted":[25],"to":[26,41,49,65,69,73,140,144],"both":[27],"monophonic":[28],"in":[32,146,171],"polyphonic":[33,46,147],"music.":[34,47],"A":[35,159],"vocal":[36],"separation":[37],"algorithm":[38],"applied":[40],"separate":[42],"Due":[48],"lack":[51],"annotated":[53],"databases,":[55],"recognizer":[57,137],"trained":[59,113,125],"speech":[61,116],"linearly":[63],"adapted":[64],"singing.":[66],"Global":[67],"adaptation":[68,88],"found":[72],"improve":[74],"recognition":[76],"performance.":[77],"Further":[78],"improvement":[79],"obtained":[81],"gender-specific":[83],"adaptation.":[84],"We":[85,100],"also":[86,169],"study":[87],"with":[89],"multiple":[90],"base":[91],"classes":[92],"defined":[93],"either":[95],"or":[97],"acoustic":[98],"similarity.":[99],"test":[101],"phoneme-level":[102],"word-level":[104,121],"n-gram":[105],"language":[106,110,122],"models.":[107],"phoneme":[109],"models":[111],"are":[112,134],"on":[114,126,164],"database":[117,128],"text.":[118],"large-vocabulary":[120],"textual":[130,142],"lyrics.":[131],"Two":[132],"applications":[133],"presented.":[135],"used":[139],"align":[141],"lyrics":[143],"vocals":[145],"music,":[148],"obtaining":[149],"an":[150],"average":[151],"error":[152],"0.94":[154],"seconds":[155],"for":[156],"line-level":[157],"alignment.":[158],"query-by-singing":[160],"retrieval":[161],"application":[162],"based":[163],"recognized":[166],"constructed;":[170],"57&#37;":[172],"cases,":[175],"first":[177],"retrieved":[178],"song":[179],"correct":[182],"one.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
