{"id":"https://openalex.org/W2787748320","doi":"https://doi.org/10.1109/apsipa.2017.8282025","title":"Non-native speech conversion with consistency-aware recursive network and generative adversarial network","display_name":"Non-native speech conversion with consistency-aware recursive network and generative adversarial network","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787748320","doi":"https://doi.org/10.1109/apsipa.2017.8282025","mag":"2787748320"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5111732740","display_name":"K. Oyamada","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keisuke Oyamada","raw_affiliation_strings":["Division of Policy and Planning Sciences, University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Division of Policy and Planning Sciences, University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065032042","display_name":"Hiroyasu Ando","orcid":"https://orcid.org/0000-0003-1102-2291"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroyasu Ando","raw_affiliation_strings":["Center for Artificial Intelligent Research, University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligent Research, University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112132273","display_name":"Kaoru Hiramatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaoru Hiramatsu","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunio Kashino","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111732740"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":2.5352,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92084874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"182","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9918000102043152,"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/pronunciation","display_name":"Pronunciation","score":0.8526809811592102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878315448760986},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6099589467048645},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.597470760345459},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5793815851211548},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5467126369476318},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.521552562713623},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5213938355445862},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.512689471244812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5088803768157959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49807238578796387},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4806331694126129},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3466983437538147},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07421597838401794}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8526809811592102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878315448760986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6099589467048645},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.597470760345459},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5793815851211548},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5467126369476318},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.521552562713623},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5213938355445862},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.512689471244812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5088803768157959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49807238578796387},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4806331694126129},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3466983437538147},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07421597838401794},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W648143168","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1903029394","https://openalex.org/W1974745215","https://openalex.org/W1977362459","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2095705004","https://openalex.org/W2099471712","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2120847449","https://openalex.org/W2125389028","https://openalex.org/W2127520494","https://openalex.org/W2129082420","https://openalex.org/W2131062138","https://openalex.org/W2145094598","https://openalex.org/W2194775991","https://openalex.org/W2218318129","https://openalex.org/W2293049663","https://openalex.org/W2293293689","https://openalex.org/W2396043161","https://openalex.org/W2406654659","https://openalex.org/W2471520273","https://openalex.org/W2473388484","https://openalex.org/W2595449219","https://openalex.org/W2666408839","https://openalex.org/W2951523806","https://openalex.org/W2964121744","https://openalex.org/W2997574889","https://openalex.org/W4320013936","https://openalex.org/W6621378261","https://openalex.org/W6631190155","https://openalex.org/W6644567525","https://openalex.org/W6653852971","https://openalex.org/W6672305501","https://openalex.org/W6674330103","https://openalex.org/W6678815747","https://openalex.org/W6681096077","https://openalex.org/W6688386640","https://openalex.org/W6697018959","https://openalex.org/W6734837653"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W2183593636","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,108],"the":[4,9,15,24,48,83,86,104,109,122],"problem":[5],"of":[6,11,18,40,51,54,66,74,85,111,124,135],"automatically":[7],"correcting":[8,32],"pronunciation":[10,16,33],"non-native":[12,19],"speakers.":[13],"Since":[14],"characteristics":[17],"speakers":[20],"depend":[21],"heavily":[22],"on":[23],"context":[25],"(such":[26],"as":[27,68],"words),":[28],"conversion":[29,50,136],"rules":[30],"for":[31],"should":[34],"be":[35],"learned":[36],"from":[37],"a":[38,44,58,64,72,77,95,129],"sequence":[39,65,73,107],"features":[41,67,75,88],"rather":[42],"than":[43],"single-frame":[45],"feature.":[46],"For":[47],"online":[49],"local":[52],"sequences":[53],"features,":[55],"we":[56,93,120],"construct":[57],"neural":[59],"network":[60,100],"(NN)":[61],"that":[62],"takes":[63],"an":[69],"input/output,":[70],"generates":[71],"in":[76,133],"segment-by-":[78],"segment":[79],"fashion":[80],"and":[81,117],"guarantees":[82],"consistency":[84],"generated":[87,105],"within":[89],"overlapped":[90],"segments.":[91],"Futhermore,":[92],"apply":[94],"recently":[96],"proposed":[97,126],"generative":[98],"adversarial":[99],"(GAN)-based":[101],"postfilter":[102],"to":[103],"feature":[106],"aim":[110],"synthesizing":[112],"natural-sounding":[113],"speech.":[114],"Through":[115],"subjective":[116],"quantitative":[118],"evaluations,":[119],"confirmed":[121],"superiority":[123],"our":[125],"method":[127],"over":[128],"conventional":[130],"NN":[131],"approach":[132],"terms":[134],"quality.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}