{"id":"https://openalex.org/W2902751174","doi":"https://doi.org/10.23919/eusipco.2018.8553333","title":"Automatic Speech Pronunciation Correction with Dynamic Frequency Warping-Based Spectral Conversion","display_name":"Automatic Speech Pronunciation Correction with Dynamic Frequency Warping-Based Spectral Conversion","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2902751174","doi":"https://doi.org/10.23919/eusipco.2018.8553333","mag":"2902751174"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2018.8553333","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","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/A5079710814","display_name":"Nobukatsu Hojo","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":true,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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 Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"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":"Kou Tanaka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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 Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079710814"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.5077,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75038087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2310","last_page":"2314"},"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":0.9975000023841858,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7830020189285278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642537355422974},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.6732994914054871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6513925194740295},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5948054790496826},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4650394320487976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3650069832801819},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08868885040283203}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7830020189285278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642537355422974},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.6732994914054871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6513925194740295},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5948054790496826},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4650394320487976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3650069832801819},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08868885040283203},{"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:10.23919/eusipco.2018.8553333","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W23142961","https://openalex.org/W62664237","https://openalex.org/W659550629","https://openalex.org/W1509691205","https://openalex.org/W1963778986","https://openalex.org/W1995752403","https://openalex.org/W1995803408","https://openalex.org/W2007786502","https://openalex.org/W2013996527","https://openalex.org/W2017742648","https://openalex.org/W2023728986","https://openalex.org/W2118154032","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2129082420","https://openalex.org/W2136166660","https://openalex.org/W2142733218","https://openalex.org/W2143076222","https://openalex.org/W2156477760","https://openalex.org/W2163283184","https://openalex.org/W2169652224","https://openalex.org/W2395578248","https://openalex.org/W2544164552","https://openalex.org/W6600922454","https://openalex.org/W6684123134","https://openalex.org/W6711777497"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698","https://openalex.org/W2340348677","https://openalex.org/W2130799169","https://openalex.org/W127416991"],"abstract_inverted_index":{"This":[0,66,95],"paper":[1,96],"deals":[2],"with":[3,54,163],"the":[4,21,56,71,113,120,123,137],"problem":[5,12,67],"of":[6,34,41,60,115,179],"pronunciation":[7,114],"conversion":[8,36,79,85,103],"(PC)":[9],"task,":[10],"a":[11,31,38,46,82,153,176,184],"to":[13,45,70,104,122,131,171,183],"reduce":[14],"non-native":[15],"accents":[16,182],"in":[17,89,126,152],"speech":[18,62,117],"while":[19,174],"preserving":[20],"original":[22,57,172],"speaker":[23,58,83,138,169,173],"identity.":[24],"Although":[25],"PC":[26,47,111,162],"can":[27],"be":[28,51],"regarded":[29],"as":[30,146],"special":[32],"class":[33],"voice":[35],"(VC),":[37],"straightforward":[39],"application":[40],"conventional":[42,185],"VC":[43,55,187],"methods":[44],"task":[48],"would":[49],"not":[50],"successful":[52],"since":[53],"identity":[59,139],"input":[61,116],"may":[63],"also":[64],"change.":[65],"is":[68,140],"due":[69],"fact":[72],"that":[73,160],"two":[74],"functions,":[75],"namely":[76],"an":[77,90],"accent":[78],"function":[80],"and":[81],"similarity":[84,170],"function,":[86],"are":[87,149],"entangled":[88],"acoustic":[91],"feature":[92],"mapping":[93],"function.":[94],"proposes":[97],"dynamic":[98],"frequency":[99,155],"warping":[100],"(DFW)-based":[101],"spectral":[102,164],"solve":[105],"this":[106],"problem.":[107],"The":[108],"proposed":[109],"DFW-based":[110,161],"converts":[112],"by":[118],"relocating":[119],"formants":[121],"corresponding":[124],"positions":[125],"which":[127],"native":[128],"speakers":[129],"tend":[130],"locate":[132],"their":[133],"formants.":[134],"We":[135],"expect":[136],"preserved":[141],"because":[142],"other":[143],"factors":[144],"such":[145],"formant":[147],"powers":[148],"kept":[150],"unchanged.":[151],"low":[154],"domain":[156],"evaluation":[157],"results":[158],"confirmed":[159],"residual":[165],"modeling":[166],"showed":[167],"higher":[168],"showing":[175],"comparable":[177],"effect":[178],"reducing":[180],"foreign":[181],"GMM-based":[186],"method.":[188]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-05T06:14:27.290980","created_date":"2025-10-10T00:00:00"}