{"id":"https://openalex.org/W2059239154","doi":"https://doi.org/10.1109/sped.2013.6682644","title":"Singing voice identification and lyrics transcription for music information retrieval invited paper","display_name":"Singing voice identification and lyrics transcription for music information retrieval invited paper","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2059239154","doi":"https://doi.org/10.1109/sped.2013.6682644","mag":"2059239154"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2013.6682644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2013.6682644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)","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/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079981416"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.3192,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.58152747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"10"},"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":0.9990000128746033,"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":0.9986000061035156,"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":0.9614032506942749},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9518192410469055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7451269626617432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.72314453125},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5995492339134216},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5457755923271179},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4981675148010254},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.494629830121994},{"id":"https://openalex.org/keywords/vocal-music","display_name":"Vocal music","score":0.43110066652297974},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.4156894385814667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33399859070777893},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24899116158485413},{"id":"https://openalex.org/keywords/music","display_name":"Music","score":0.1256353259086609},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11510223150253296},{"id":"https://openalex.org/keywords/music-education","display_name":"Music education","score":0.09440559148788452},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09072387218475342},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.08191066980361938},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.06795653700828552}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9614032506942749},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9518192410469055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7451269626617432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72314453125},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5995492339134216},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5457755923271179},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4981675148010254},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.494629830121994},{"id":"https://openalex.org/C553614217","wikidata":"https://www.wikidata.org/wiki/Q685884","display_name":"Vocal music","level":4,"score":0.43110066652297974},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.4156894385814667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33399859070777893},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24899116158485413},{"id":"https://openalex.org/C535889608","wikidata":"https://www.wikidata.org/wiki/Q638","display_name":"Music","level":3,"score":0.1256353259086609},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11510223150253296},{"id":"https://openalex.org/C13553968","wikidata":"https://www.wikidata.org/wiki/Q27908","display_name":"Music education","level":2,"score":0.09440559148788452},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09072387218475342},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.08191066980361938},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.06795653700828552},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2013.6682644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2013.6682644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W112239495","https://openalex.org/W129413713","https://openalex.org/W153815065","https://openalex.org/W168903045","https://openalex.org/W178884067","https://openalex.org/W178932670","https://openalex.org/W182406043","https://openalex.org/W182831726","https://openalex.org/W1560013842","https://openalex.org/W1570504315","https://openalex.org/W1604012244","https://openalex.org/W1964208564","https://openalex.org/W2002342963","https://openalex.org/W2057745663","https://openalex.org/W2068398811","https://openalex.org/W2107288886","https://openalex.org/W2111935391","https://openalex.org/W2121178298","https://openalex.org/W2122830402","https://openalex.org/W2123169318","https://openalex.org/W2124867748","https://openalex.org/W2148154194","https://openalex.org/W2150574373","https://openalex.org/W2152591660","https://openalex.org/W2154591323","https://openalex.org/W2156063339","https://openalex.org/W2156230116","https://openalex.org/W2164282073","https://openalex.org/W2168987487","https://openalex.org/W2169410099","https://openalex.org/W2174404816","https://openalex.org/W2394955069","https://openalex.org/W2398871418","https://openalex.org/W2403272360","https://openalex.org/W2407692080","https://openalex.org/W4235128394","https://openalex.org/W6604617924","https://openalex.org/W6606268758","https://openalex.org/W6607288479","https://openalex.org/W6607294247","https://openalex.org/W6607423309","https://openalex.org/W6634309418","https://openalex.org/W6636121673","https://openalex.org/W6682384985","https://openalex.org/W6682825961","https://openalex.org/W6712099778","https://openalex.org/W6712736788","https://openalex.org/W6713370510","https://openalex.org/W6713555227"],"related_works":["https://openalex.org/W2994064478","https://openalex.org/W2144707026","https://openalex.org/W2515398186","https://openalex.org/W112239495","https://openalex.org/W2542820473","https://openalex.org/W2130068930","https://openalex.org/W3081404490","https://openalex.org/W2012665501","https://openalex.org/W126167045","https://openalex.org/W4212956476"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,57],"overview":[4],"of":[5,12,24,41,53,60,68,101,118,156],"methods":[6],"and":[7,21,49,158],"applications":[8,168],"dealing":[9,95],"with":[10,91,96,163],"analysis":[11],"singing":[13,69,97,104,123],"voice":[14,46],"audio":[15,36,159],"signals,":[16],"related":[17],"to":[18,45,109,131],"singer":[19],"identity":[20],"lyrics":[22,120,157],"content":[23],"the":[25,51,61,110,119,145,149],"singing.":[26],"Singer":[27],"identification":[28,47],"in":[29,75,103,134],"polyphonic":[30,76],"music":[31,77],"is":[32,43,56,84,124,129,160],"based":[33,143],"on":[34,144],"general":[35],"classification":[37,67],"methods.":[38],"The":[39,63,99,114],"presence":[40],"instruments":[42],"detrimental":[44],"performance,":[48],"eliminating":[50],"effect":[52],"instrumental":[54],"accompaniment":[55],"important":[58],"aspect":[59],"prob-lem.":[62],"results":[64],"show":[65],"that":[66],"voices":[70],"can":[71],"be":[72,132],"done":[73],"robustly":[74],"when":[78],"using":[79],"source":[80],"separation.":[81],"Lyrics":[82],"transcription":[83,121],"approached":[85],"as":[86,170],"a":[87,106,135,140],"speech":[88,111],"recognition":[89,112,116],"prob-lem,":[90],"specific":[92],"elements":[93],"for":[94,138,153,166],"voice.":[98],"variability":[100],"phonation":[102],"poses":[105],"significant":[107],"challenge":[108],"approach.":[113],"word":[115],"accuracy":[117],"from":[122,148],"quite":[125],"low,":[126],"but":[127],"it":[128],"shown":[130],"useful":[133],"query-by-singing":[136],"application,":[137],"performing":[139],"textual":[141],"search":[142],"words":[146],"recognized":[147],"query.":[150],"A":[151],"system":[152],"automatic":[154,171],"alignment":[155],"also":[161],"presented,":[162],"sufficient":[164],"performance":[165],"facilitating":[167],"such":[169],"karaoke":[172],"annotation":[173],"or":[174],"song":[175],"browsing.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
