{"id":"https://openalex.org/W2759925408","doi":"https://doi.org/10.1109/icassp.2017.7953089","title":"Adapting and controlling DNN-based speech synthesis using input codes","display_name":"Adapting and controlling DNN-based speech synthesis using input codes","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2759925408","doi":"https://doi.org/10.1109/icassp.2017.7953089","mag":"2759925408"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/6009b390-771b-4fd6-bc3c-096818a9a852","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002145453","display_name":"Hieu-Thi Luong","orcid":"https://orcid.org/0000-0002-4772-5995"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["JP","VN"],"is_corresponding":true,"raw_author_name":"Hieu-Thi Luong","raw_affiliation_strings":["The National Institute of Informatics, Japan","VNUHCM-University of Science, Ho Chi Minh City, Vietnam"],"affiliations":[{"raw_affiliation_string":"The National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"VNUHCM-University of Science, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002145453"],"corresponding_institution_ids":["https://openalex.org/I123565023","https://openalex.org/I184597095","https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":11.0081,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.98611288,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4905","last_page":"4909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9882000088691711,"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/T12031","display_name":"Speech and dialogue systems","score":0.9754999876022339,"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":0.804762601852417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7315897941589355},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5993651151657104},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5403919219970703},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4993464946746826},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4981882572174072},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4850260615348816},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4691027104854584},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4499267041683197},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4151002764701843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3178938627243042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804762601852417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7315897941589355},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5993651151657104},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5403919219970703},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4993464946746826},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4981882572174072},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4850260615348816},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4691027104854584},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4499267041683197},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4151002764701843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3178938627243042},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2017.7953089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/6009b390-771b-4fd6-bc3c-096818a9a852","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/6009b390-771b-4fd6-bc3c-096818a9a852","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/6009b390-771b-4fd6-bc3c-096818a9a852","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/6009b390-771b-4fd6-bc3c-096818a9a852","pdf_url":"http://hdl.handle.net/20.500.11820/6009b390-771b-4fd6-bc3c-096818a9a852","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":"Luong, H-T, Takaki, S, Henter, G & Yamagishi, J 2017, Adapting and Controlling DNN-Based Speech Synthesis Using Input Codes. in The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2017. Institute of Electrical and Electronics Engineers, pp. 1905-1909, 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, Louisiana, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7953089","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/6009b390-771b-4fd6-bc3c-096818a9a852","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/6009b390-771b-4fd6-bc3c-096818a9a852","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2759925408.pdf","grobid_xml":"https://content.openalex.org/works/W2759925408.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W165283731","https://openalex.org/W192649799","https://openalex.org/W1492383498","https://openalex.org/W1570874634","https://openalex.org/W1783473872","https://openalex.org/W1984905644","https://openalex.org/W1993409002","https://openalex.org/W2031321541","https://openalex.org/W2039800941","https://openalex.org/W2042600255","https://openalex.org/W2043003570","https://openalex.org/W2087110403","https://openalex.org/W2094147890","https://openalex.org/W2102003408","https://openalex.org/W2112021726","https://openalex.org/W2152205330","https://openalex.org/W2154920538","https://openalex.org/W2156692643","https://openalex.org/W2294797155","https://openalex.org/W2395849284","https://openalex.org/W2399550240","https://openalex.org/W2400063444","https://openalex.org/W2402539796","https://openalex.org/W2405144467","https://openalex.org/W2406264770","https://openalex.org/W2516321201","https://openalex.org/W2516559027","https://openalex.org/W2517266855","https://openalex.org/W2598638573","https://openalex.org/W2605320104","https://openalex.org/W6606787761","https://openalex.org/W6634436088","https://openalex.org/W6638081404","https://openalex.org/W6675380101","https://openalex.org/W6682918086","https://openalex.org/W6683161958","https://openalex.org/W6696843773","https://openalex.org/W6713871409","https://openalex.org/W6736204136"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Methods":[0],"for":[1,122],"adapting":[2],"and":[3,38,61,84,88,176,179],"controlling":[4],"the":[5,21,69,146,152,166,186],"characteristics":[6,66,150],"of":[7,23,57,81,100,131,151,173],"output":[8],"speech":[9,14,65,76],"are":[10],"important":[11],"topics":[12],"in":[13,28,43],"synthesis.":[15],"In":[16],"this":[17],"work,":[18],"we":[19,90,96,114,136],"investigated":[20],"performance":[22],"DNN-based":[24],"text-to-speech":[25],"systems":[26],"that":[27,158,177],"parallel":[29],"to":[30,45,102,144],"conventional":[31],"text":[32],"input":[33,70,141],"also":[34],"take":[35],"speaker,":[36],"gender,":[37],"age":[39,149],"codes":[40],"as":[41],"inputs,":[42],"order":[44],"1)":[46,94],"perform":[47,51],"multi-speaker":[48,106,160],"synthesis,":[49],"2)":[50,112],"speaker":[52,110,116],"adaptation":[53,59,117,132,178],"using":[54,165,185],"small":[55,129],"amounts":[56],"target-speaker":[58],"data,":[60],"3)":[62,134],"modify":[63],"synthetic":[64],"based":[67],"on":[68],"codes.":[71,111,187],"Using":[72],"a":[73,98,104,128,171],"large-scale,":[74],"studio-quality":[75],"corpus":[77],"with":[78,109,138,170],"135":[79],"speakers":[80,101,124],"both":[82],"genders":[83],"ages":[85],"between":[86],"tens":[87],"eighties,":[89],"performed":[91,115,183],"three":[92],"experiments:":[93],"First,":[95],"used":[97],"subset":[99],"construct":[103],"DNN-based,":[105],"acoustic":[107],"model":[108],"Next,":[113],"by":[118],"estimating":[119],"code":[120,142,168],"vectors":[121,143,169],"new":[123],"via":[125],"backpropagation":[126],"from":[127],"amount":[130],"material.":[133],"Finally,":[135],"experimented":[137],"manually":[139],"manipulating":[140],"alter":[145],"gender":[147],"and/or":[148],"synthesised":[153],"speech.":[154],"Experimental":[155],"results":[156],"show":[157],"high-performance":[159],"models":[161],"can":[162,181],"be":[163,182],"constructed":[164],"proposed":[167],"variety":[172],"encoding":[174],"schemes,":[175],"manipulation":[180],"effectively":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}