{"id":"https://openalex.org/W2954099406","doi":"https://doi.org/10.21437/interspeech.2019-2571","title":"Fine-Grained Robust Prosody Transfer for Single-Speaker Neural Text-To-Speech","display_name":"Fine-Grained Robust Prosody Transfer for Single-Speaker Neural Text-To-Speech","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2954099406","doi":"https://doi.org/10.21437/interspeech.2019-2571","mag":"2954099406"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2571","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1907.02479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004616142","display_name":"Srikanth Ronanki","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":"Srikanth Ronanki","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050067836","display_name":"Jonas Rohnke","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":"Jonas Rohnke","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"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":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.2819,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64769698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4440","last_page":"4444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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":0.9958999752998352,"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/prosody","display_name":"Prosody","score":0.9058138132095337},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7603147029876709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6893833875656128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44680607318878174},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33133167028427124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32515424489974976}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9058138132095337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7603147029876709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6893833875656128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44680607318878174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33133167028427124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32515424489974976}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2571","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.02479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.02479","pdf_url":"https://arxiv.org/pdf/1907.02479","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:2954099406","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.02479","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.1907.02479","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.02479","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.02479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.02479","pdf_url":"https://arxiv.org/pdf/1907.02479","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954099406.pdf","grobid_xml":"https://content.openalex.org/works/W2954099406.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1922655562","https://openalex.org/W2056457557","https://openalex.org/W2091735588","https://openalex.org/W2107740512","https://openalex.org/W2116046013","https://openalex.org/W2397375888","https://openalex.org/W2518172956","https://openalex.org/W2794490148","https://openalex.org/W2888922217","https://openalex.org/W2901620353","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2941649920","https://openalex.org/W2949836599","https://openalex.org/W2951004968","https://openalex.org/W2962691331","https://openalex.org/W2963542120","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2973227003"],"related_works":["https://openalex.org/W2973158936","https://openalex.org/W3164064632","https://openalex.org/W3163677684","https://openalex.org/W3163929126","https://openalex.org/W2949526695","https://openalex.org/W2314487624","https://openalex.org/W2045011345","https://openalex.org/W2584404039","https://openalex.org/W3133664532","https://openalex.org/W3204661432","https://openalex.org/W2305940569","https://openalex.org/W3198815374","https://openalex.org/W3015975959","https://openalex.org/W2950224550","https://openalex.org/W3009940588","https://openalex.org/W3137585377","https://openalex.org/W2916104401","https://openalex.org/W2594927458","https://openalex.org/W3022377205","https://openalex.org/W3133801870"],"abstract_inverted_index":{"We":[0,107,121,140,159],"present":[1],"a":[2,30,42,62,103,109,143],"neural":[3],"text-to-speech":[4,105],"system":[5],"for":[6,17],"fine-grained":[7],"prosody":[8,19,27,47,119,134],"transfer":[9,20,48],"from":[10,66,79,136],"one":[11],"speaker":[12,55],"to":[13,33,54,94,112,145],"another.":[14],"Conventional":[15],"approaches":[16],"end-to-end":[18],"typically":[21],"use":[22,92,147],"either":[23],"fixed-dimensional":[24],"or":[25],"variable-length":[26],"embedding":[28],"via":[29],"secondary":[31],"attention":[32],"encode":[34],"the":[35,45,59,75,80,115,146,151,154],"reference":[36,63,76,155],"signal.":[37],"However,":[38],"when":[39],"trained":[40],"on":[41],"single-speaker":[43],"dataset,":[44],"conventional":[46],"systems":[49],"are":[50],"not":[51],"robust":[52],"enough":[53],"variability,":[56],"especially":[57],"in":[58,149],"case":[60,148],"of":[61,74,118,153],"signal":[64,77,156],"coming":[65],"an":[67,137],"unseen":[68,138],"speaker.":[69,139],"Therefore,":[70],"we":[71,86],"propose":[72,142],"decoupling":[73],"alignment":[78],"overall":[81],"system.":[82,106],"For":[83],"this":[84],"purpose,":[85],"pre-compute":[87],"phoneme-level":[88],"time":[89],"stamps":[90],"and":[91,131,168],"them":[93,101],"aggregate":[95],"prosodic":[96],"features":[97],"per":[98],"phoneme,":[99],"injecting":[100],"into":[102],"sequence-to-sequence":[104],"incorporate":[108],"variational":[110],"auto-encoder":[111],"further":[113],"enhance":[114],"latent":[116],"representation":[117],"embeddings.":[120],"show":[122],"that":[123],"our":[124,162],"proposed":[125,163],"approach":[126],"is":[127,157],"significantly":[128],"more":[129],"stable":[130],"achieves":[132],"reliable":[133],"transplantation":[135],"also":[141],"solution":[144],"which":[150],"transcription":[152],"absent.":[158],"evaluate":[160],"all":[161],"methods":[164],"using":[165],"both":[166],"objective":[167],"subjective":[169],"listening":[170],"tests.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}