{"id":"https://openalex.org/W3196867271","doi":"https://doi.org/10.21437/ssw.2016-19","title":"Multi-output RNN-LSTM for multiple speaker speech synthesis with \u03b1-interpolation model","display_name":"Multi-output RNN-LSTM for multiple speaker speech synthesis with \u03b1-interpolation model","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W3196867271","doi":"https://doi.org/10.21437/ssw.2016-19","mag":"3196867271"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2016-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/bc55fa58-067a-40bb-80c8-c76c98bae50f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101557983","display_name":"Santiago Pascual","orcid":"https://orcid.org/0000-0002-8365-7387"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101557983"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.8887,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86381059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"112","last_page":"117"},"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":0.9947999715805054,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7895503044128418},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.7415822744369507},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.7377239465713501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.708016037940979},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5835844278335571},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4581453204154968},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4405781030654907},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4128914475440979},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41211050748825073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3712475001811981},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.14941245317459106},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.075492262840271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895503044128418},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.7415822744369507},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.7377239465713501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.708016037940979},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5835844278335571},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4581453204154968},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4405781030654907},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4128914475440979},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41211050748825073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3712475001811981},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.14941245317459106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.075492262840271},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/ssw.2016-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/bc55fa58-067a-40bb-80c8-c76c98bae50f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bc55fa58-067a-40bb-80c8-c76c98bae50f","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini Botinhao, C, Wang, X, Takaki, S & Yamagishi, J 2016, Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech. in Proceedings of 9th ISCA Speech Synthesis Workshop. Sunnyvale, United States, pp. 159-165, 9th ISCA Speech Synthesis Workshop , Sunnyvale, California, United States, 13/09/16. https://doi.org/10.21437/SSW.2016-19","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/bc55fa58-067a-40bb-80c8-c76c98bae50f","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/bc55fa58-067a-40bb-80c8-c76c98bae50f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini Botinhao, C, Wang, X, Takaki, S & Yamagishi, J 2016, Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech. in Proceedings of 9th ISCA Speech Synthesis Workshop. Sunnyvale, United States, pp. 159-165, 9th ISCA Speech Synthesis Workshop , Sunnyvale, California, United States, 13/09/16. https://doi.org/10.21437/SSW.2016-19","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:upcommons.upc.edu:2117/105484","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/105484","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/bc55fa58-067a-40bb-80c8-c76c98bae50f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bc55fa58-067a-40bb-80c8-c76c98bae50f","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini Botinhao, C, Wang, X, Takaki, S & Yamagishi, J 2016, Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech. in Proceedings of 9th ISCA Speech Synthesis Workshop. Sunnyvale, United States, pp. 159-165, 9th ISCA Speech Synthesis Workshop , Sunnyvale, California, United States, 13/09/16. https://doi.org/10.21437/SSW.2016-19","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W1484172358","https://openalex.org/W1538607601","https://openalex.org/W1576227399","https://openalex.org/W2069143585","https://openalex.org/W2076638338","https://openalex.org/W2095705004","https://openalex.org/W2102003408","https://openalex.org/W2107860279","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2150341604","https://openalex.org/W2150658333","https://openalex.org/W2228674556","https://openalex.org/W2294797155","https://openalex.org/W2295406225","https://openalex.org/W2338806053","https://openalex.org/W2394662942","https://openalex.org/W2401942008","https://openalex.org/W2406189128","https://openalex.org/W2562274522","https://openalex.org/W2964060510"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"has":[2],"been":[3],"applied":[4],"successfully":[5],"to":[6,105],"speech":[7,17],"processing.":[8],"In":[9],"this":[10,47],"paper":[11],"we":[12,61],"propose":[13],"an":[14],"architecture":[15],"for":[16,38],"synthesis":[18],"using":[19],"multiple":[20],"speakers.":[21,96,111],"Some":[22],"hidden":[23],"layers":[24],"are":[25],"shared":[26],"by":[27,69],"all":[28],"the":[29,64,79,88,100,107],"speakers,":[30],"while":[31],"there":[32],"is":[33,85],"a":[34,71],"specific":[35],"output":[36,73],"layer":[37,74,89],"each":[39],"speaker.":[40],"Objective":[41],"and":[42],"perceptual":[43],"experiments":[44],"prove":[45],"that":[46,99],"scheme":[48],"produces":[49],"much":[50],"better":[51],"results":[52],"in":[53],"comparison":[54],"with":[55,91],"sin-":[56],"gle":[57],"speaker":[58,67],"model.":[59],"Moreover,":[60],"also":[62],"tackle":[63],"problem":[65],"of":[66,78,94],"interpolation":[68],"adding":[70],"new":[72],"(a-layer)":[75],"on":[76],"top":[77],"multi-output":[80],"branches.":[81],"An":[82],"identifying":[83],"code":[84],"injected":[86],"into":[87],"together":[90],"acoustic":[92,108],"features":[93,109],"many":[95],"Experiments":[97],"show":[98],"a-layer":[101],"can":[102],"effectively":[103],"learn":[104],"interpolate":[106],"between":[110]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}