{"id":"https://openalex.org/W3129478200","doi":"https://doi.org/10.1109/icassp39728.2021.9414395","title":"Low Resource Audio-To-Lyrics Alignment from Polyphonic Music Recordings","display_name":"Low Resource Audio-To-Lyrics Alignment from Polyphonic Music Recordings","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3129478200","doi":"https://doi.org/10.1109/icassp39728.2021.9414395","mag":"3129478200"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.09202","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":false,"raw_author_name":"Emir Demirel","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","[Queen Mary University of London,Centre for Digital Music,UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"[Queen Mary University of London,Centre for Digital Music,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":[{"id":"https://openalex.org/I4210089335","display_name":"Perfect Harmony Health","ror":"https://ror.org/00835yh61","country_code":"US","type":"other","lineage":["https://openalex.org/I4210089335"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sven Ahlback","raw_affiliation_strings":["Doremir Music Research AB,SE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doremir Music Research AB,SE","institution_ids":["https://openalex.org/I4210089335"]}]},{"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":["Queen Mary University of London,Centre for Digital Music,UK","[Queen Mary University of London,Centre for Digital Music,UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"[Queen Mary University of London,Centre for Digital Music,UK]","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1813,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29403644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"586","last_page":"590"},"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":0.9997000098228455,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.9466196894645691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7892289161682129},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6577170491218567},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5542334318161011},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.543032705783844},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5291391015052795},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4394221901893616},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.4210091531276703},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4184706211090088},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3736662268638611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34602922201156616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14818784594535828},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14568641781806946},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12413430213928223}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9466196894645691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892289161682129},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6577170491218567},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5542334318161011},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.543032705783844},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5291391015052795},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4394221901893616},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.4210091531276703},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4184706211090088},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3736662268638611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34602922201156616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14818784594535828},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14568641781806946},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12413430213928223},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.09202","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09202","pdf_url":"https://arxiv.org/pdf/2102.09202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97930","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97930","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97930/2/Dixon%20Low%20Resource%20Audio%202024%20Accepted.pdf","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":null},{"id":"mag:3129478200","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.09202","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:123456789/75798","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/75798","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.2102.09202","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.09202","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},{"id":"doi:10.17023/814w-ja64","is_oa":true,"landing_page_url":"https://doi.org/10.17023/814w-ja64","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.09202","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09202","pdf_url":"https://arxiv.org/pdf/2102.09202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W40088496","https://openalex.org/W93815243","https://openalex.org/W182406043","https://openalex.org/W1164175658","https://openalex.org/W2105961775","https://openalex.org/W2144827818","https://openalex.org/W2288371874","https://openalex.org/W2292656914","https://openalex.org/W2514741789","https://openalex.org/W2802201485","https://openalex.org/W2903006902","https://openalex.org/W2917340025","https://openalex.org/W2935701729","https://openalex.org/W2963452667","https://openalex.org/W2972411915","https://openalex.org/W2973975824","https://openalex.org/W2981585590","https://openalex.org/W2990594533","https://openalex.org/W3090751054","https://openalex.org/W3108719139","https://openalex.org/W6600436803","https://openalex.org/W6603836127","https://openalex.org/W6607423309","https://openalex.org/W6627665034","https://openalex.org/W6751512325","https://openalex.org/W6768315578","https://openalex.org/W6786603260","https://openalex.org/W6787042052"],"related_works":["https://openalex.org/W3163088658","https://openalex.org/W2917340025","https://openalex.org/W3187239407","https://openalex.org/W2028766658","https://openalex.org/W2498398271","https://openalex.org/W2935701729","https://openalex.org/W83475003","https://openalex.org/W2911113553","https://openalex.org/W3158877740","https://openalex.org/W2025791157","https://openalex.org/W3108719139","https://openalex.org/W182406043","https://openalex.org/W2903006902","https://openalex.org/W2075180943","https://openalex.org/W3189624906","https://openalex.org/W3174257816","https://openalex.org/W2955316069","https://openalex.org/W1988945913","https://openalex.org/W2020625454","https://openalex.org/W3117303186"],"abstract_inverted_index":{"Lyrics":[0],"alignment":[1,27,67,80,99,145],"in":[2,12],"long":[3],"music":[4,40,104],"recordings":[5,105],"can":[6],"be":[7],"memory":[8,31],"exhaustive":[9],"when":[10],"performed":[11,69],"a":[13,21,29,65,121],"single":[14],"pass.":[15],"In":[16,93],"this":[17],"study,":[18],"we":[19,95,114,149],"present":[20],"novel":[22],"method":[23],"that":[24,77],"performs":[25,82],"audio-to-lyrics":[26,79],"with":[28,84,154],"low":[30],"consumption":[32],"footprint":[33],"regardless":[34],"of":[35,38,123,133],"the":[36,39,47,51,59,72,85,103,111,116,131,134,142,155],"duration":[37],"recording.":[41],"The":[42],"proposed":[43],"system":[44,81,100],"first":[45],"spots":[46],"anchoring":[48],"words":[49],"within":[50],"audio":[52],"signal.":[53],"With":[54],"respect":[55],"to":[56,70,101],"these":[57],"anchors,":[58],"recording":[60],"is":[61,68],"then":[62],"segmented":[63,112],"and":[64,144],"second-pass":[66],"obtain":[71],"word":[73],"timings.":[74],"We":[75],"show":[76],"our":[78,97,128,152],"competitively":[83],"state-of-the-art,":[86],"while":[87],"requiring":[88],"much":[89],"less":[90],"computational":[91],"resources.":[92],"addition,":[94],"utilize":[96],"lyrics":[98,117],"segment":[102],"into":[106],"sentence-level":[107],"chunks.":[108],"Notably":[109],"on":[110,120,141],"recordings,":[113],"report":[115],"transcription":[118,143],"scores":[119],"number":[122],"benchmark":[124],"test":[125],"sets.":[126],"Finally,":[127],"experiments":[129],"highlight":[130],"importance":[132],"source":[135],"separation":[136],"step":[137],"for":[138],"good":[139],"performance":[140],"tasks.":[146],"For":[147],"reproducibility,":[148],"publicly":[150],"share":[151],"code":[153],"research":[156],"community.":[157]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
