{"id":"https://openalex.org/W3176782192","doi":"https://doi.org/10.23919/eusipco54536.2021.9616147","title":"Computational Pronunciation Analysis in Sung Utterances","display_name":"Computational Pronunciation Analysis in Sung Utterances","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3176782192","doi":"https://doi.org/10.23919/eusipco54536.2021.9616147","mag":"3176782192"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616147","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616147","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/2106.10977","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, 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"],"raw_orcid":null,"affiliations":[{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Doremir Music Research AB,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doremir Music Research AB,Stockholm,Sweden","institution_ids":[]}]}],"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":0.1269,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33031423,"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":"186","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.9132366180419922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8043928742408752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6346731185913086},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6131962537765503},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5702995657920837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.549229085445404},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5463006496429443},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5431901216506958},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4773024320602417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4759863615036011},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.44400155544281006},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.4269876480102539},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.4160063564777374},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1839960515499115}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9132366180419922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043928742408752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6346731185913086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6131962537765503},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5702995657920837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.549229085445404},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5463006496429443},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5431901216506958},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4773024320602417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4759863615036011},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44400155544281006},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4269876480102539},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.4160063564777374},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1839960515499115},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":6,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616147","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616147","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.10977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.10977","pdf_url":"https://arxiv.org/pdf/2106.10977","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":"","raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97929","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97929","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97929/2/Dixon%20Computational%20Pronunciation%20Analysis%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":""},{"id":"mag:3176782192","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.10977","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:123456789/79688","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/79688","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.2106.10977","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.10977","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:2106.10977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.10977","pdf_url":"https://arxiv.org/pdf/2106.10977","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3176782192.pdf","grobid_xml":"https://content.openalex.org/works/W3176782192.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W645911330","https://openalex.org/W1581879603","https://openalex.org/W1847682101","https://openalex.org/W1895481600","https://openalex.org/W2009955221","https://openalex.org/W2029757240","https://openalex.org/W2038412242","https://openalex.org/W2053347927","https://openalex.org/W2067709094","https://openalex.org/W2079623482","https://openalex.org/W2118774185","https://openalex.org/W2142416747","https://openalex.org/W2167870003","https://openalex.org/W2400997536","https://openalex.org/W2404375817","https://openalex.org/W2514741789","https://openalex.org/W2577008904","https://openalex.org/W2888867175","https://openalex.org/W2889429804","https://openalex.org/W2917340025","https://openalex.org/W2949977994","https://openalex.org/W2973071600","https://openalex.org/W2973975824","https://openalex.org/W3090751054","https://openalex.org/W4248060224","https://openalex.org/W6631362777","https://openalex.org/W6636598300","https://openalex.org/W6636811518","https://openalex.org/W6680893734","https://openalex.org/W6732426729","https://openalex.org/W6768315578"],"related_works":["https://openalex.org/W2165280259","https://openalex.org/W1565662837","https://openalex.org/W45930974","https://openalex.org/W3143175244","https://openalex.org/W2073211979","https://openalex.org/W2062096622","https://openalex.org/W2810104656","https://openalex.org/W2979112046","https://openalex.org/W2117160306","https://openalex.org/W2142851794","https://openalex.org/W3157841565","https://openalex.org/W654092675","https://openalex.org/W2308727","https://openalex.org/W2547418329","https://openalex.org/W2166610164","https://openalex.org/W2571838890","https://openalex.org/W2156230116","https://openalex.org/W2154853451","https://openalex.org/W2170681008","https://openalex.org/W2937402758"],"abstract_inverted_index":{"Recent":[0],"automatic":[1],"lyrics":[2],"transcription":[3],"(ALT)":[4],"approaches":[5],"focus":[6],"on":[7,31,53,76],"building":[8],"stronger":[9],"acoustic":[10],"models":[11],"or":[12],"in-domain":[13],"language":[14,84],"models,":[15],"while":[16],"the":[17,32,65,73,90],"pronunciation":[18,33,43],"aspect":[19],"is":[20,51],"seldom":[21],"touched":[22],"upon.":[23],"This":[24],"paper":[25],"applies":[26],"a":[27,41,79,97],"novel":[28],"computational":[29],"analysis":[30],"variances":[34],"in":[35,69,78,94],"sung":[36],"utterances":[37],"and":[38],"further":[39],"proposes":[40],"new":[42,98],"model":[44,50],"adapted":[45],"for":[46,102],"singing.":[47],"The":[48],"singing-adapted":[49],"tested":[52],"multiple":[54],"public":[55],"datasets":[56],"via":[57],"word":[58],"recognition":[59],"experiments.":[60],"It":[61],"performs":[62],"better":[63],"than":[64],"standard":[66],"speech":[67],"dictionary":[68],"all":[70],"settings":[71],"reporting":[72],"best":[74],"results":[75],"ALT":[77],"capella":[80],"recordings":[81],"using":[82],"n-gram":[83],"models.":[85],"For":[86],"reproducibility,":[87],"we":[88],"share":[89],"sentence-level":[91],"annotations":[92],"used":[93],"testing,":[95],"providing":[96],"benchmark":[99],"evaluation":[100],"set":[101],"ALT.":[103]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}