{"id":"https://openalex.org/W2507389969","doi":"https://doi.org/10.21437/ssw.2016-25","title":"Speaker Adaptation of Various Components in Deep Neural Network based Speech Synthesis","display_name":"Speaker Adaptation of Various Components in Deep Neural Network based Speech Synthesis","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W2507389969","doi":"https://doi.org/10.21437/ssw.2016-25","mag":"2507389969"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2016-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-25","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics (NII), Tokyo, 101-8430, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics (NII), Tokyo, 101-8430, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105988176","display_name":"Sang-Jin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SangJin Kim","raw_affiliation_strings":["Naver Labs, Naver Corporation, Seongnam, 463-867, Korea"],"affiliations":[{"raw_affiliation_string":"Naver Labs, Naver Corporation, Seongnam, 463-867, Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"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 (NII), Tokyo, 101-8430, Japan","University of Edinburgh, Edinburgh, EH8 9LW, United Kingdom"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics (NII), Tokyo, 101-8430, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"University of Edinburgh, Edinburgh, EH8 9LW, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062895056"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":2.6503,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92050852,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"159"},"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/T11309","display_name":"Music and Audio Processing","score":0.9866999983787537,"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":0.9858999848365784,"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":0.7615156173706055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7586700916290283},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6800335645675659},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5893667340278625},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5667734146118164},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5306039452552795},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5300374031066895},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5242474675178528},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5228167772293091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.477704793214798},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4437127113342285},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4281764328479767},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42439591884613037},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37544146180152893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615156173706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7586700916290283},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6800335645675659},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5893667340278625},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5667734146118164},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5306039452552795},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5300374031066895},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5242474675178528},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5228167772293091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.477704793214798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4437127113342285},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4281764328479767},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42439591884613037},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37544146180152893},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2016-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-25","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:publications/120e60f2-946e-4303-9ad7-dd29075ef391","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/speaker-adaptation-of-various-components-in-deep-neural-network-based-speech-synthesis(120e60f2-946e-4303-9ad7-dd29075ef391).html","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W80543058","https://openalex.org/W129217914","https://openalex.org/W1514737389","https://openalex.org/W1567690964","https://openalex.org/W1770758908","https://openalex.org/W1778816975","https://openalex.org/W1813659000","https://openalex.org/W1861150963","https://openalex.org/W1989549063","https://openalex.org/W1992463165","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2020024436","https://openalex.org/W2049686551","https://openalex.org/W2056738732","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2093632031","https://openalex.org/W2094147890","https://openalex.org/W2095425517","https://openalex.org/W2102003408","https://openalex.org/W2145247325","https://openalex.org/W2153750031","https://openalex.org/W2153914468","https://openalex.org/W2294797155","https://openalex.org/W2394662942","https://openalex.org/W2400654494","https://openalex.org/W2605320104","https://openalex.org/W4235154690"],"related_works":["https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2121652828","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,65,114],"investigate":[4],"the":[5,94],"effectiveness":[6],"of":[7,111],"speaker":[8,31,85],"adaptation":[9,32,86,112,116],"for":[10,40,48,125],"various":[11],"essential":[12],"components":[13,77,102],"in":[14,74],"deep":[15,129],"neural":[16],"network":[17],"based":[18,80,117,131],"speech":[19,71,143],"synthesis,":[20],"including":[21],"acoustic":[22,24,54,95,127],"models,":[23,128],"feature":[25,132],"extraction,":[26,133],"and":[27,120,134,138],"post-filters.In":[28],"general,":[29],"a":[30,68,84,108],"technique,":[33],"e.g.,":[34],"maximum":[35],"likelihood":[36],"linear":[37],"regression":[38],"(MLLR)":[39],"HMMs":[41],"or":[42,61],"learning":[43],"hidden":[44],"unit":[45],"contributions":[46],"(LHUC)":[47],"DNNs,":[49,83],"is":[50],"applied":[51,90],"to":[52,57,93,100],"an":[53],"modeling":[55,96],"part":[56,97],"change":[58],"voice":[59],"characteristics":[60],"speaking":[62],"styles.However,":[63],"since":[64],"have":[66],"proposed":[67],"multiple":[69],"DNN-based":[70,135],"synthesis":[72,144],"system,":[73],"which":[75],"several":[76],"are":[78],"represented":[79,103],"on":[81,118],"feed-forward":[82],"technique":[87],"can":[88],"be":[89],"not":[91],"only":[92],"but":[98],"also":[99],"other":[101],"by":[104],"DNNs.In":[105],"experiments":[106],"using":[107,146],"small":[109],"amount":[110],"data,":[113],"performed":[115],"LHUC":[119],"simple":[121],"additional":[122],"fine":[123],"tuning":[124],"DNNbased":[126],"auto-encoder":[130],"post-filter":[136],"models":[137],"compared":[139],"them":[140],"with":[141],"HMM-based":[142],"systems":[145],"MLLR.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}