{"id":"https://openalex.org/W2606052883","doi":"https://doi.org/10.21437/interspeech.2017-1420","title":"A Neural Parametric Singing Synthesizer","display_name":"A Neural Parametric Singing Synthesizer","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2606052883","doi":"https://doi.org/10.21437/interspeech.2017-1420","mag":"2606052883"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1420","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/1704.03809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005810332","display_name":"Merlijn Blaauw","orcid":"https://orcid.org/0000-0001-8051-9942"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Merlijn Blaauw","raw_affiliation_strings":["Pompeu Fabra University, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Pompeu Fabra University, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060417258","display_name":"Jordi Bonada","orcid":"https://orcid.org/0000-0002-8671-0729"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Bonada","raw_affiliation_strings":["Pompeu Fabra University, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Pompeu Fabra University, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005810332"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":3.5445,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.93754682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4001","last_page":"4005"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7908440828323364},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7125338315963745},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.63536536693573},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.573409914970398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5296230912208557},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4697081446647644},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4286682605743408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36480408906936646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32112976908683777},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30970996618270874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13412165641784668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908440828323364},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7125338315963745},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.63536536693573},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.573409914970398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5296230912208557},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4697081446647644},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4286682605743408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36480408906936646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32112976908683777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30970996618270874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13412165641784668},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2017-1420","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/35951","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/35951","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:1704.03809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.03809","pdf_url":"https://arxiv.org/pdf/1704.03809","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":"mag:2606052883","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1704.03809.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":"doi:10.48550/arxiv.1704.03809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.03809","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:1704.03809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.03809","pdf_url":"https://arxiv.org/pdf/1704.03809","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G3402661218","display_name":null,"funder_award_id":"TIN2015-70816-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1576227399","https://openalex.org/W1990505856","https://openalex.org/W2102870814","https://openalex.org/W2516406502","https://openalex.org/W2949382160","https://openalex.org/W2949650786","https://openalex.org/W2963840672","https://openalex.org/W2964115871","https://openalex.org/W2964121744","https://openalex.org/W2964122153"],"related_works":["https://openalex.org/W2471520273","https://openalex.org/W2949382160","https://openalex.org/W2964243274","https://openalex.org/W2515336442","https://openalex.org/W2049686551","https://openalex.org/W1522301498","https://openalex.org/W3163031268","https://openalex.org/W2945993525","https://openalex.org/W2982133652","https://openalex.org/W3208292940","https://openalex.org/W3210679021","https://openalex.org/W2928550135","https://openalex.org/W2963103134","https://openalex.org/W2968397919","https://openalex.org/W3015338123","https://openalex.org/W3124061379","https://openalex.org/W3132136936","https://openalex.org/W3098869438","https://openalex.org/W2899882692","https://openalex.org/W2994785103"],"abstract_inverted_index":{"We":[0,137],"present":[1],"a":[2,10,27,102,120,134,153,169,181],"new":[3],"model":[4,23,63,107],"for":[5],"singing":[6],"synthesis":[7],"based":[8],"on":[9,50],"modified":[11],"version":[12],"of":[13,18,34,159],"the":[14,32,79,92,106,110,160,177],"WaveNet":[15],"architecture.":[16],"Instead":[17],"modeling":[19],"raw":[20],"waveform,":[21],"we":[22,84,100,172],"features":[24],"produced":[25],"by":[26],"parametric":[28,143],"vocoder":[29],"that":[30],"separates":[31],"influence":[33],"pitch":[35,42],"and":[36,55,59,108,126,145,152,179,188],"timbre.":[37],"This":[38],"allows":[39],"conveniently":[40],"modifying":[41],"to":[43,77,87,104,116,141,165],"match":[44],"any":[45],"target":[46],"melody,":[47],"facilitates":[48],"training":[49,58],"more":[51,114],"modest":[52],"dataset":[53],"sizes,":[54],"significantly":[56],"reduces":[57],"generation":[60,112,162],"times.":[61],"Our":[62],"makes":[64],"frame-wise":[65],"predictions":[66],"using":[67,149,168],"mixture":[68],"density":[69],"outputs":[70,74],"rather":[71],"than":[72],"categorical":[73],"in":[75,97,133,185],"order":[76],"reduce":[78],"required":[80],"parameter":[81],"count.":[82],"As":[83],"found":[85],"overfitting":[86],"be":[88,131,166],"an":[89],"issue":[90],"with":[91],"relatively":[93],"small":[94],"datasets":[95],"used":[96],"our":[98,139],"experiments,":[99],"propose":[101],"method":[103,140],"regularize":[105],"make":[109],"autoregressive":[111,161],"process":[113,178],"robust":[115],"prediction":[117],"errors.":[118],"Using":[119],"simple":[121],"multi-stream":[122],"architecture,":[123],"harmonic,":[124],"aperiodic":[125],"voiced/unvoiced":[127],"components":[128],"can":[129,173],"all":[130],"predicted":[132],"coherent":[135],"manner.":[136],"compare":[138],"existing":[142],"statistical":[144],"state-of-the-art":[146],"concatenative":[147],"methods":[148],"quantitative":[150],"metrics":[151],"listening":[154],"test.":[155],"While":[156],"naive":[157],"implementations":[158],"algorithm":[163,171],"tend":[164],"inefficient,":[167],"smart":[170],"greatly":[174],"speed":[175,187],"up":[176],"obtain":[180],"system":[182],"that's":[183],"competitive":[184],"both":[186],"quality.":[189]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}