{"id":"https://openalex.org/W2994986888","doi":"https://doi.org/10.21437/interspeech.2020-1399","title":"Singing Synthesis: With a Little Help from my Attention","display_name":"Singing Synthesis: With a Little Help from my Attention","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W2994986888","doi":"https://doi.org/10.21437/interspeech.2020-1399","mag":"2994986888"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1399","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/1912.05881","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083300352","display_name":"Orazio Angelini","orcid":"https://orcid.org/0000-0002-5057-7866"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Orazio Angelini","raw_affiliation_strings":["King's College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London, London, United Kingdom","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","orcid":null},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Alexis Moinet","raw_affiliation_strings":["University of Mons, Mons, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":["Toshiba (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6573,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63787125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1221","last_page":"1225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9894000291824341,"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/naturalness","display_name":"Naturalness","score":0.9362500905990601},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8443578481674194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7120298147201538},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.7118135094642639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6427809000015259},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6161441802978516},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5435142517089844},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5209214091300964},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.473276823759079},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19694578647613525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1271604597568512},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08276370167732239}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9362500905990601},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8443578481674194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120298147201538},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.7118135094642639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6427809000015259},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6161441802978516},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5435142517089844},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5209214091300964},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.473276823759079},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19694578647613525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1271604597568512},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08276370167732239},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1399","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.05881","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.05881","pdf_url":"https://arxiv.org/pdf/1912.05881","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":null},{"id":"mag:2994986888","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1912.05881v1","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":"doi:10.48550/arxiv.1912.05881","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.05881","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.05881","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.05881","pdf_url":"https://arxiv.org/pdf/1912.05881","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":null},"sustainable_development_goals":[{"score":0.49000000953674316,"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/W2994986888.pdf","grobid_xml":"https://content.openalex.org/works/W2994986888.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2030149476","https://openalex.org/W2124097505","https://openalex.org/W2407080277","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2606052883","https://openalex.org/W2778460379","https://openalex.org/W2792995953","https://openalex.org/W2793133856","https://openalex.org/W2847144333","https://openalex.org/W2901796276","https://openalex.org/W2919624000","https://openalex.org/W2921576841","https://openalex.org/W2922346874","https://openalex.org/W2937242376","https://openalex.org/W2963272440","https://openalex.org/W2963403868","https://openalex.org/W2963542120","https://openalex.org/W2963609956","https://openalex.org/W2963654953","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2973158936","https://openalex.org/W2984106626","https://openalex.org/W2987843471","https://openalex.org/W3015645837"],"related_works":["https://openalex.org/W3096437652","https://openalex.org/W3015922793","https://openalex.org/W3015843452","https://openalex.org/W2258901759","https://openalex.org/W2972892814","https://openalex.org/W2725043152","https://openalex.org/W3021832621","https://openalex.org/W3025521275","https://openalex.org/W319297663","https://openalex.org/W20372203","https://openalex.org/W1584278479","https://openalex.org/W17607154","https://openalex.org/W3082779874","https://openalex.org/W2613634895","https://openalex.org/W2962946733","https://openalex.org/W35498557","https://openalex.org/W2546373232","https://openalex.org/W2488485539","https://openalex.org/W3034514362","https://openalex.org/W3100400819"],"abstract_inverted_index":{"We":[0],"present":[1],"UTACO,":[2],"a":[3,14,97,162],"singing":[4,43,55,107],"synthesis":[5,56,108],"model":[6,111],"based":[7,16],"on":[8,17],"an":[9],"attention-based":[10],"sequence-to-sequence":[11],"mechanism":[12],"and":[13,58,82,84,122],"vocoder":[15],"dilated":[18],"causal":[19],"convolutions.":[20],"These":[21],"two":[22],"classes":[23],"of":[24,31,42,64,74,153,161],"models":[25,89],"have":[26,34],"significantly":[27],"affected":[28],"the":[29,40,54,62,65,91,130,150,159],"field":[30,57],"text-to-speech,":[32],"but":[33],"never":[35],"been":[36],"thoroughly":[37],"applied":[38,52],"to":[39,53,104,124,129,148,156],"task":[41],"synthesis.":[44],"UTACO":[45],"demonstrates":[46],"that":[47],"attention":[48],"can":[49],"be":[50],"successfully":[51],"improves":[59],"naturalness":[60,101],"over":[61],"state":[63],"art.":[66],"The":[67,110],"system":[68],"requires":[69],"considerably":[70],"less":[71],"explicit":[72,142],"modelling":[73,144],"voice":[75],"features":[76],"such":[77],"as":[78,120],"F0":[79],"patterns,":[80],"vibratos,":[81],"note":[83],"phoneme":[85],"durations,":[86],"than":[87],"previous":[88,105],"in":[90,100],"literature.":[92],"Despite":[93],"this,":[94],"it":[95,145],"shows":[96],"strong":[98],"improvement":[99],"with":[102,140],"respect":[103],"neural":[106],"models.":[109],"does":[112],"not":[113],"require":[114],"any":[115,141],"durations":[116],"or":[117],"pitch":[118],"patterns":[119],"inputs,":[121],"learns":[123],"insert":[125],"vibrato":[126],"autonomously":[127],"according":[128],"musical":[131],"context.":[132],"However,":[133],"we":[134],"observe":[135],"that,":[136],"by":[137],"completely":[138],"dispensing":[139],"duration":[143],"becomes":[146],"harder":[147],"obtain":[149],"fine":[151],"control":[152],"timing":[154],"needed":[155],"exactly":[157],"match":[158],"tempo":[160],"song.":[163]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
