{"id":"https://openalex.org/W3004823919","doi":"https://doi.org/10.1109/icassp40776.2020.9053436","title":"Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior","display_name":"Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3004823919","doi":"https://doi.org/10.1109/icassp40776.2020.9053436","mag":"3004823919"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/2002.03788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077772423","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0002-5886-056X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101989491","display_name":"Yuan Cao","orcid":"https://orcid.org/0000-0002-2495-4701"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Cao","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghui Wu","raw_affiliation_strings":["Google Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6699","last_page":"6703"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.69484543800354},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6930176019668579},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6856685280799866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6759964823722839},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5819236040115356},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5698318481445312},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5076049566268921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028397440910339},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4626605808734894},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41038447618484497},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3905523419380188},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35525813698768616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1519630253314972},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08985495567321777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.69484543800354},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6930176019668579},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6856685280799866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6759964823722839},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5819236040115356},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5698318481445312},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5076049566268921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028397440910339},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4626605808734894},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41038447618484497},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3905523419380188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35525813698768616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1519630253314972},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08985495567321777},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.03788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.03788","pdf_url":"https://arxiv.org/pdf/2002.03788","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3004823919","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.03788.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.2002.03788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.03788","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":"Preprint"},{"id":"doi:10.17023/rq23-3t54","is_oa":true,"landing_page_url":"https://doi.org/10.17023/rq23-3t54","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:2002.03788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.03788","pdf_url":"https://arxiv.org/pdf/2002.03788","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3004823919.pdf","grobid_xml":"https://content.openalex.org/works/W3004823919.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W592244745","https://openalex.org/W1494198834","https://openalex.org/W1959608418","https://openalex.org/W2069859485","https://openalex.org/W2091425152","https://openalex.org/W2107740512","https://openalex.org/W2107860279","https://openalex.org/W2130942839","https://openalex.org/W2752796333","https://openalex.org/W2766812927","https://openalex.org/W2795109282","https://openalex.org/W2898727538","https://openalex.org/W2901997113","https://openalex.org/W2907262790","https://openalex.org/W2936774411","https://openalex.org/W2948238043","https://openalex.org/W2962714411","https://openalex.org/W2962824709","https://openalex.org/W2963272440","https://openalex.org/W2963382687","https://openalex.org/W2963403868","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972359262","https://openalex.org/W6617744952","https://openalex.org/W6629717138","https://openalex.org/W6640284076","https://openalex.org/W6640963894","https://openalex.org/W6675938391","https://openalex.org/W6679436768","https://openalex.org/W6739901393","https://openalex.org/W6745697700","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6756197946","https://openalex.org/W6756385397","https://openalex.org/W6763316926"],"related_works":["https://openalex.org/W2964243274","https://openalex.org/W3016021263","https://openalex.org/W3015440759","https://openalex.org/W2904459034","https://openalex.org/W2785390226","https://openalex.org/W3024605872","https://openalex.org/W2963609956","https://openalex.org/W2795109282","https://openalex.org/W2897548994","https://openalex.org/W3125709657","https://openalex.org/W2586950923","https://openalex.org/W3049360585","https://openalex.org/W2566781703","https://openalex.org/W3125481789","https://openalex.org/W2996743179","https://openalex.org/W3095018479","https://openalex.org/W2936295285","https://openalex.org/W2363702666","https://openalex.org/W2116842019","https://openalex.org/W2123523384"],"abstract_inverted_index":{"Recent":[0],"neural":[1],"text-to-speech":[2],"(TTS)":[3],"models":[4,19],"with":[5,40,52],"fine-grained":[6,23],"latent":[7,29,67,82],"features":[8,30,83],"enable":[9],"precise":[10],"control":[11],"of":[12,15,108,116],"the":[13,41,81,97,101,123,128,142,153],"prosody":[14,117],"synthesized":[16],"speech.":[17],"Such":[18],"typically":[20],"incorporate":[21],"a":[22,61,65],"variational":[24],"autoencoder":[25],"(VAE)":[26],"structure,":[27],"extracting":[28],"at":[31],"each":[32],"input":[33],"token":[34],"(e.g.,":[35],"phonemes).":[36],"However,":[37],"generating":[38],"samples":[39],"standard":[42],"VAE":[43],"prior":[44,63,94],"often":[45],"results":[46,120],"in":[47,64,130],"unnatural":[48],"and":[49,88,114],"discontinuous":[50],"speech,":[51],"dramatic":[53],"prosodic":[54],"variation":[55],"between":[56],"tokens.":[57],"This":[58,76],"paper":[59],"proposes":[60],"sequential":[62],"discrete":[66],"space":[68],"which":[69],"can":[70,145],"generate":[71],"more":[72],"naturally":[73],"sounding":[74],"samples.":[75],"is":[77],"accomplished":[78],"by":[79],"discretizing":[80],"using":[84,103],"vector":[85],"quantization":[86],"(VQ),":[87],"separately":[89],"training":[90],"an":[91],"autoregressive":[92],"(AR)":[93],"model":[95,125,144],"over":[96],"result.":[98],"We":[99],"evaluate":[100],"approach":[102],"listening":[104],"tests,":[105],"objective":[106],"metrics":[107],"automatic":[109],"speech":[110],"recognition":[111],"(ASR)":[112],"performance,":[113],"measurements":[115],"attributes.":[118],"Experimental":[119],"show":[121],"that":[122,138],"proposed":[124,143],"significantly":[126],"improves":[127],"naturalness":[129],"random":[131],"sample":[132],"generation.":[133],"Furthermore,":[134],"initial":[135],"experiments":[136],"demonstrate":[137],"randomly":[139],"sampling":[140],"from":[141],"be":[146],"used":[147],"as":[148],"data":[149],"augmentation":[150],"to":[151],"improve":[152],"ASR":[154],"performance.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-03-05T00:00:00"}