{"id":"https://openalex.org/W3041718022","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207052","title":"Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-Attention","display_name":"Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-Attention","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3041718022","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207052","mag":"3041718022"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.06486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079906910","display_name":"Emir Demirel","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":"Emir Demirel","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK","Queen Mary University of London Centre for Digital Music London UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London Centre for Digital Music London UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073161410","display_name":"Sven Ahlb\u00e4ck","orcid":"https://orcid.org/0000-0002-4756-1441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sven Ahlback","raw_affiliation_strings":["Doremir Music Research AB, Stockholm, Sweden","Doremir Music Research AB,Stockholm,Sweden"],"affiliations":[{"raw_affiliation_string":"Doremir Music Research AB, Stockholm, Sweden","institution_ids":[]},{"raw_affiliation_string":"Doremir Music Research AB,Stockholm,Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"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":"Simon Dixon","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK","Queen Mary University of London Centre for Digital Music London UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London Centre for Digital Music London UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079906910"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.2743,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63710738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9970999956130981,"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":0.9567704200744629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784894585609436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6488399505615234},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6135058999061584},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5816730260848999},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5580317974090576},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5400636196136475},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5158302187919617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5078831315040588},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5062614679336548},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4804260730743408},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4786909222602844},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43815991282463074},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4151827096939087},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3202337622642517},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0944940447807312},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0886925458908081}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9567704200744629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784894585609436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6488399505615234},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6135058999061584},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5816730260848999},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5580317974090576},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5400636196136475},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5158302187919617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5078831315040588},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5062614679336548},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4804260730743408},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4786909222602844},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43815991282463074},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4151827096939087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3202337622642517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0944940447807312},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0886925458908081},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.06486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.06486","pdf_url":"https://arxiv.org/pdf/2007.06486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3041718022","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2007.06486.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/68991","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/68991","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"doi:10.48550/arxiv.2007.06486","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.06486","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.06486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.06486","pdf_url":"https://arxiv.org/pdf/2007.06486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3041718022.pdf","grobid_xml":"https://content.openalex.org/works/W3041718022.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W2002342963","https://openalex.org/W2026369565","https://openalex.org/W2046932483","https://openalex.org/W2059239154","https://openalex.org/W2079623482","https://openalex.org/W2131342762","https://openalex.org/W2144731719","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2514973355","https://openalex.org/W2577008904","https://openalex.org/W2747135936","https://openalex.org/W2795138957","https://openalex.org/W2802023636","https://openalex.org/W2802201485","https://openalex.org/W2889152503","https://openalex.org/W2889429804","https://openalex.org/W2963403868","https://openalex.org/W2964089206","https://openalex.org/W2964150074","https://openalex.org/W2973071600","https://openalex.org/W2973975824","https://openalex.org/W2981585590","https://openalex.org/W3015315843","https://openalex.org/W6631362777","https://openalex.org/W6681443795","https://openalex.org/W6713762819","https://openalex.org/W6732426729","https://openalex.org/W6739901393","https://openalex.org/W6750705186","https://openalex.org/W6755207826","https://openalex.org/W6756588447"],"related_works":["https://openalex.org/W3090751054","https://openalex.org/W2945891342","https://openalex.org/W3203269426","https://openalex.org/W2932491493","https://openalex.org/W2955075648","https://openalex.org/W2962824709","https://openalex.org/W3110663778","https://openalex.org/W2940073716","https://openalex.org/W3197464192","https://openalex.org/W3168566645","https://openalex.org/W3007776460","https://openalex.org/W3175709363","https://openalex.org/W3091926439","https://openalex.org/W3091088345","https://openalex.org/W2971766686","https://openalex.org/W2899551440","https://openalex.org/W3132072393","https://openalex.org/W3135281744","https://openalex.org/W3194316524","https://openalex.org/W2996155272"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,41],"is":[2,102,142],"a":[3,52,82,171],"well":[4],"developed":[5],"research":[6],"field":[7],"so":[8],"that":[9],"the":[10,14,24,40,88,128,139,150,156,165,175],"current":[11],"state":[12],"of":[13,42,130,138,152],"art":[15],"systems":[16],"are":[17,114,125],"being":[18],"used":[19,93],"in":[20,23,94,133,167],"many":[21],"applications":[22],"software":[25],"industry,":[26],"yet":[27],"as":[28,63],"by":[29],"today,":[30],"there":[31],"still":[32],"does":[33],"not":[34],"exist":[35],"such":[36],"robust":[37],"system":[38,160],"for":[39,55,86,174],"words":[43],"and":[44,118,149,169],"sentences":[45],"from":[46],"singing":[47],"voice.":[48],"This":[49],"paper":[50],"proposes":[51],"complete":[53],"pipeline":[54],"this":[56,95],"task":[57],"which":[58,124],"may":[59],"commonly":[60],"be":[61],"referred":[62],"automatic":[64],"lyrics":[65,129],"transcription":[66],"(ALT).":[67],"We":[68],"have":[69,105],"trained":[70,126],"convolutional":[71],"time-delay":[72],"neural":[73],"networks":[74],"with":[75,107],"self-attention":[76,140],"on":[77,127],"monophonic":[78],"karaoke":[79],"recordings":[80],"using":[81],"sequence":[83],"classification":[84],"objective":[85],"building":[87],"acoustic":[89],"model.":[90],"The":[91],"dataset":[92],"study,":[96],"DAMP":[97],"-":[98],"Sing!":[99],"300x30x2":[100],"[1]":[101],"filtered":[103],"to":[104,164],"songs":[106,132],"only":[108],"English":[109],"lyrics.":[110],"Different":[111],"language":[112],"models":[113],"tested":[115],"including":[116],"MaxEnt":[117],"Recurrent":[119],"Neural":[120],"Networks":[121],"based":[122],"methods":[123],"pop":[131],"English.":[134],"An":[135],"in-depth":[136],"analysis":[137],"mechanism":[141],"held":[143],"while":[144],"tuning":[145],"its":[146],"context":[147],"width":[148],"number":[151],"attention":[153],"heads.":[154],"Using":[155],"best":[157],"settings,":[158],"our":[159],"achieves":[161],"notable":[162],"improvement":[163],"state-of-the-art":[166],"ALT":[168],"provides":[170],"new":[172],"baseline":[173],"task.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
