{"id":"https://openalex.org/W3162770051","doi":"https://doi.org/10.1109/icassp39728.2021.9414444","title":"Universal Neural Vocoding with Parallel Wavenet","display_name":"Universal Neural Vocoding with Parallel Wavenet","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162770051","doi":"https://doi.org/10.1109/icassp39728.2021.9414444","mag":"3162770051"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414444","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062423359","display_name":"Yunlong Jiao","orcid":"https://orcid.org/0000-0002-0776-0550"},"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":"Yunlong Jiao","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031116817","display_name":"Adam Gabry\u015b","orcid":null},"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":"Adam Gabrys","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021310105","display_name":"Georgi Tinchev","orcid":"https://orcid.org/0000-0002-9910-6598"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgi Tinchev","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046126186","display_name":"Bartosz Putrycz","orcid":null},"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":"Bartosz Putrycz","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"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":"Daniel Korzekwa","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026578737","display_name":"Viacheslav Klimkov","orcid":null},"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":"Viacheslav Klimkov","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1285,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9646389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6044","last_page":"6048"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/naturalness","display_name":"Naturalness","score":0.9063729643821716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777596116065979},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5894128680229187},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.539883553981781},{"id":"https://openalex.org/keywords/universality","display_name":"Universality (dynamical systems)","score":0.5344962477684021},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5208276510238647},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48350170254707336},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4212302565574646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3697776794433594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35281020402908325}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9063729643821716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777596116065979},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5894128680229187},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.539883553981781},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.5344962477684021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5208276510238647},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48350170254707336},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4212302565574646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3697776794433594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35281020402908325},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414444","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2604184139","https://openalex.org/W2619368999","https://openalex.org/W2769810959","https://openalex.org/W2786868129","https://openalex.org/W2888169323","https://openalex.org/W2900295214","https://openalex.org/W2901707128","https://openalex.org/W2954386831","https://openalex.org/W2963300588","https://openalex.org/W2963522141","https://openalex.org/W2963712897","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964281804","https://openalex.org/W2964307104","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3103913581","https://openalex.org/W3125708547","https://openalex.org/W4287761884","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6734815144","https://openalex.org/W6736356763","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6755592152","https://openalex.org/W6755802933","https://openalex.org/W6756511606","https://openalex.org/W6765987481","https://openalex.org/W6767111847","https://openalex.org/W6779337556"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"We":[0,33,64,76],"present":[1],"a":[2,27],"universal":[3,19,69],"neural":[4,86],"vocoder":[5,20,70,82,87],"based":[6],"on":[7,26,36,103],"Parallel":[8],"WaveNet,":[9],"with":[10],"an":[11],"additional":[12],"conditioning":[13],"network":[14],"called":[15],"Audio":[16],"Encoder.":[17],"Our":[18],"offers":[21],"real-time":[22],"high-quality":[23],"speech":[24],"synthesis":[25],"wide":[28],"range":[29],"of":[30,40,52,91],"use":[31],"cases.":[32],"tested":[34],"it":[35],"43":[37],"internal":[38],"speakers":[39],"diverse":[41],"age":[42],"and":[43,56,93],"gender,":[44],"speaking":[45],"20":[46],"languages":[47],"in":[48,89],"17":[49],"unique":[50],"styles,":[51],"which":[53],"7":[54],"voices":[55],"5":[57],"styles":[58],"were":[59],"not":[60],"exposed":[61],"during":[62],"training.":[63],"show":[65,78],"that":[66,79],"the":[67,80],"proposed":[68,81],"significantly":[71],"outperforms":[72,83],"speaker-dependent":[73],"vocoders":[74],"overall.":[75],"also":[77],"several":[84],"existing":[85],"architectures":[88],"terms":[90],"naturalness":[92],"universality.":[94],"These":[95],"findings":[96],"are":[97],"consistent":[98],"when":[99],"we":[100],"further":[101],"test":[102],"more":[104],"than":[105],"300":[106],"open-source":[107],"voices.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}