{"id":"https://openalex.org/W4414140869","doi":"https://doi.org/10.1109/icmew68306.2025.11152264","title":"Exploiting Music Source Separation for Automatic Lyrics Transcription with Whisper","display_name":"Exploiting Music Source Separation for Automatic Lyrics Transcription with Whisper","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414140869","doi":"https://doi.org/10.1109/icmew68306.2025.11152264"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5008206524","display_name":"J.U.I. Syed","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jaza Syed","raw_affiliation_strings":["Queen Mary University of London,School of Electronic Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of Electronic Engineering and Computer Science","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119598516","display_name":"Ivan Meresman Higgs","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ivan Meresman Higgs","raw_affiliation_strings":["Queen Mary University of London,School of Electronic Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of Electronic Engineering and Computer Science","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073040966","display_name":"Ond\u0159ej C\u00edfka","orcid":"https://orcid.org/0000-0002-6268-6445"},"institutions":[{"id":"https://openalex.org/I4210105771","display_name":"Endometriosis","ror":"https://ror.org/01q5m4507","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210105771"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ond\u0159ej C\u00edfka","raw_affiliation_strings":["AudioShake"],"affiliations":[{"raw_affiliation_string":"AudioShake","institution_ids":["https://openalex.org/I4210105771"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076173089","display_name":"M. Sandler","orcid":"https://orcid.org/0000-0002-5691-8107"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Sandler","raw_affiliation_strings":["Queen Mary University of London,School of Electronic Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of Electronic Engineering and Computer Science","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008206524"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":1.5372,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85863304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9944000244140625,"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":0.9936000108718872,"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":0.8224999904632568},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6642000079154968},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.579200029373169},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5170000195503235},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49709999561309814},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.42739999294281006},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4065000116825104},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.36890000104904175}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8224999904632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519000172615051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6974999904632568},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.579200029373169},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.42739999294281006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41510000824928284},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4065000116825104},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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":10,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2089428608","https://openalex.org/W2917340025","https://openalex.org/W3001377302","https://openalex.org/W3174257816","https://openalex.org/W4385822293","https://openalex.org/W4387870414","https://openalex.org/W4392019934","https://openalex.org/W4402115972","https://openalex.org/W4403674676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2360952181","https://openalex.org/W2597614303","https://openalex.org/W634160686","https://openalex.org/W4310670065","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W437317580"],"abstract_inverted_index":{"Automatic":[0],"lyrics":[1],"transcription":[2,128],"(ALT)":[3],"remains":[4],"a":[5,106,134,140,158,169],"challenging":[6],"task":[7],"in":[8,18,28,36,56,85,139,143,168,172],"the":[9,33,39,75,97,191,205,213],"field":[10],"of":[11,32,42,64,77,99,208],"music":[12,57],"information":[13],"retrieval,":[14],"despite":[15],"great":[16],"advances":[17,55],"automatic":[19,62],"speech":[20],"recognition":[21],"(ASR)":[22],"brought":[23],"about":[24],"by":[25],"transformer-based":[26],"architectures":[27],"recent":[29],"years.":[30],"One":[31],"major":[34],"challenges":[35],"ALT":[37,72,103,194],"is":[38],"high":[40],"amplitude":[41],"interfering":[43],"audio":[44],"signals":[45],"relative":[46,174],"to":[47,51,87,162,175],"conventional":[48],"ASR":[49,110],"due":[50],"musical":[52],"accompaniment.":[53],"Recent":[54],"source":[58,78,100,109,155,188],"separation":[59,79,101,156],"have":[60],"enabled":[61],"extraction":[63],"high-quality":[65],"separated":[66,119],"vocals,":[67,120],"which":[68,166,217],"could":[69],"potentially":[70],"improve":[71],"performance.":[73],"However,":[74],"effect":[76],"has":[80],"not":[81],"been":[82],"systematically":[83],"investigated":[84],"order":[86],"establish":[88],"best":[89],"practices":[90],"for":[91,185,216],"its":[92],"use.":[93],"This":[94],"work":[95],"examines":[96],"impact":[98],"on":[102,116,190],"using":[104,154],"Whisper,":[105],"state-of-the-art":[107,183],"open":[108,187],"model.":[111],"We":[112,201],"evaluate":[113],"Whisper\u2019s":[114,176],"performance":[115],"original":[117],"audio,":[118],"and":[121,126],"vocal":[122,159,218],"stems":[123,219],"across":[124],"short-form":[125],"long-form":[127,193,209],"tasks.":[129],"For":[130,148],"short-form,":[131],"we":[132,150],"suggest":[133],"concatenation":[135],"method":[136],"that":[137],"results":[138,167,184],"consistent":[141,170],"reduction":[142,171],"Word":[144],"Error":[145],"Rate":[146],"(WER).":[147],"long-form,":[149],"propose":[151],"an":[152,186],"algorithm":[153],"as":[157],"activity":[160],"detector":[161],"derive":[163],"segment":[164],"boundaries,":[165],"WER":[173],"native":[177],"long-<em>form":[178],"algorithm.":[179],"Our":[180],"approach":[181],"achieves":[182],"system":[189],"Jam-ALT":[192,214],"benchmark,":[195],"without":[196],"any":[197],"training":[198],"or":[199],"fine-tuning.":[200],"also":[202],"publish":[203],"MUSDB-ALT,":[204],"first":[206],"dataset":[207],"lyric":[210],"transcripts":[211],"following":[212],"guidelines":[215],"are":[220],"publicly":[221],"available.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}