{"id":"https://openalex.org/W3174856165","doi":"https://doi.org/10.21437/ssw.2021-17","title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","display_name":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3174856165","doi":"https://doi.org/10.21437/ssw.2021-17","mag":"3174856165"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","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/2106.12896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089445018","display_name":"Raahil Shah","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Raahil Shah","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000904701","display_name":"Kamil Pokora","orcid":"https://orcid.org/0009-0006-0756-4118"},"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":"Kamil Pokora","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027412678","display_name":"Abdelhamid Ezzerg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelhamid Ezzerg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026578737","display_name":"Viacheslav Klimkov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viacheslav Klimkov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058343897","display_name":"Goeric Huybrechts","orcid":"https://orcid.org/0000-0003-0222-3008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goeric Huybrechts","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046126186","display_name":"Bartosz Putrycz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bartosz Putrycz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5089445018"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08299483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"101"},"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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":0.9944999814033508,"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":0.9546085000038147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7303448915481567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6904353499412537},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.610180139541626},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5540866255760193},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44335609674453735},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.439968466758728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.308100163936615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13022899627685547},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07647040486335754},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05915874242782593}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9546085000038147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303448915481567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6904353499412537},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.610180139541626},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5540866255760193},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44335609674453735},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.439968466758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.308100163936615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13022899627685547},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07647040486335754},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05915874242782593},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/ssw.2021-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.12896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.12896","pdf_url":"https://arxiv.org/pdf/2106.12896","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":null,"raw_type":"text"},{"id":"mag:3174856165","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.12896v2","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.2106.12896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.12896","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:2106.12896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.12896","pdf_url":"https://arxiv.org/pdf/2106.12896","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174856165.pdf","grobid_xml":"https://content.openalex.org/works/W3174856165.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1710476689","https://openalex.org/W2102003408","https://openalex.org/W2125389028","https://openalex.org/W2129142580","https://openalex.org/W2576309025","https://openalex.org/W2626778328","https://openalex.org/W2666408839","https://openalex.org/W2746654391","https://openalex.org/W2777302760","https://openalex.org/W2796495654","https://openalex.org/W2889028433","https://openalex.org/W2901997113","https://openalex.org/W2946200149","https://openalex.org/W2951004968","https://openalex.org/W2962788625","https://openalex.org/W2962896155","https://openalex.org/W2963223306","https://openalex.org/W2963432880","https://openalex.org/W2963712897","https://openalex.org/W2963782041","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2969521066","https://openalex.org/W2969658393","https://openalex.org/W2972702018","https://openalex.org/W2972951102","https://openalex.org/W2973034126","https://openalex.org/W3015922793","https://openalex.org/W3022876224","https://openalex.org/W3024747869","https://openalex.org/W3081416955","https://openalex.org/W3091928890","https://openalex.org/W3096303254","https://openalex.org/W3130016944","https://openalex.org/W3161296985","https://openalex.org/W3161492781","https://openalex.org/W3162770051"],"related_works":["https://openalex.org/W3195171908","https://openalex.org/W3194347141","https://openalex.org/W3175000095","https://openalex.org/W3168527213","https://openalex.org/W3116834994","https://openalex.org/W3112470437","https://openalex.org/W3169905056","https://openalex.org/W3196001064","https://openalex.org/W3016159759","https://openalex.org/W3132489765","https://openalex.org/W3096124080","https://openalex.org/W3029282897","https://openalex.org/W2594927458","https://openalex.org/W2560410824","https://openalex.org/W2975414524","https://openalex.org/W3198104520","https://openalex.org/W3161959914","https://openalex.org/W3198332267","https://openalex.org/W3128910262","https://openalex.org/W3025528898"],"abstract_inverted_index":{"Whilst":[0],"recent":[1],"neural":[2],"text-to-speech":[3],"(TTS)":[4],"approaches":[5],"produce":[6],"high-quality":[7,31],"speech,":[8],"they":[9],"typically":[10],"require":[11],"a":[12,24,47,69,125,163],"large":[13],"amount":[14,37],"of":[15,38,53,83,108,124,135],"recordings":[16,103],"from":[17,86,156],"the":[18,36,51,87,92,100,119],"target":[19,88,136],"speaker.":[20,89],"In":[21,64],"previous":[22],"work,":[23],"3-step":[25],"method":[26,70],"was":[27],"proposed":[28,97],"to":[29,91,102,162],"generate":[30],"TTS":[32,75,160],"while":[33],"greatly":[34],"reducing":[35],"data":[39,85],"required":[40],"for":[41,56,71,106,113],"training.":[42],"However,":[43],"we":[44,67,117,145],"have":[45],"observed":[46],"ceiling":[48],"effect":[49],"in":[50],"level":[52],"naturalness":[54,107,120],"achievable":[55],"highly":[57,73],"expressive":[58,74],"voices":[59,76],"when":[60],"using":[61,131],"this":[62,65],"approach.":[63],"paper,":[66],"present":[68],"building":[72],"with":[77,140,168],"as":[78,80],"little":[79],"15":[81,133],"minutes":[82,134,142],"speech":[84,109],"Compared":[90],"current":[93],"state-of-the-art":[94],"approach,":[95],"our":[96],"improvements":[98,151],"close":[99],"gap":[101],"by":[104,111],"23.3%":[105],"and":[110,121,173],"16.3%":[112],"speaker":[114,122,137],"similarity.":[115],"Further,":[116],"match":[118],"similarity":[123],"Tacotron2-based":[126],"full-data":[127],"(~10":[128],"hours)":[129],"model":[130,161,165,172],"only":[132],"data,":[138],"whereas":[139],"30":[141],"or":[143],"more,":[144],"significantly":[146],"outperform":[147],"it.":[148],"The":[149],"following":[150],"are":[152],"proposed:":[153],"1)":[154],"changing":[155],"an":[157,169,175],"autoregressive,":[158],"attention-based":[159],"non-autoregressive":[164],"replacing":[166],"attention":[167],"external":[170],"duration":[171],"2)":[174],"additional":[176],"Conditional":[177],"Generative":[178],"Adversarial":[179],"Network":[180],"(cGAN)":[181],"based":[182],"fine-tuning":[183],"step.":[184]},"counts_by_year":[],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-25T00:00:00"}