{"id":"https://openalex.org/W2977798327","doi":"https://doi.org/10.1109/ijcnn.2019.8852225","title":"An Approach to Cross-Lingual Voice Conversion","display_name":"An Approach to Cross-Lingual Voice Conversion","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977798327","doi":"https://doi.org/10.1109/ijcnn.2019.8852225","mag":"2977798327"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5090694009","display_name":"Sai Sirisha Rallabandi","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sai Sirisha Rallabandi","raw_affiliation_strings":["Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058673990","display_name":"Suryakanth V. Gangashetty","orcid":"https://orcid.org/0000-0001-6745-4363"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakanth V Gangashetty","raw_affiliation_strings":["Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090694009"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":0.4341,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72332605,"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":"1","last_page":"7"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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":0.9830999970436096,"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":0.8493411540985107},{"id":"https://openalex.org/keywords/polyglot","display_name":"Polyglot","score":0.7593319416046143},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6048480272293091},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5861656665802002},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5646276473999023},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5221631526947021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48765623569488525},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4866953194141388},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.461956262588501},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45514845848083496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4504826068878174},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4276074767112732},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41030025482177734},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12468349933624268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493411540985107},{"id":"https://openalex.org/C2780239667","wikidata":"https://www.wikidata.org/wiki/Q2102850","display_name":"Polyglot","level":2,"score":0.7593319416046143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6048480272293091},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5861656665802002},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5646276473999023},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5221631526947021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48765623569488525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4866953194141388},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.461956262588501},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45514845848083496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4504826068878174},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4276074767112732},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41030025482177734},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12468349933624268},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W36870606","https://openalex.org/W95152782","https://openalex.org/W799143314","https://openalex.org/W1498436455","https://openalex.org/W1509691205","https://openalex.org/W1538607601","https://openalex.org/W1570450547","https://openalex.org/W1972420736","https://openalex.org/W1994616650","https://openalex.org/W1995565802","https://openalex.org/W2009797711","https://openalex.org/W2013996527","https://openalex.org/W2035962301","https://openalex.org/W2078647797","https://openalex.org/W2102409316","https://openalex.org/W2107860279","https://openalex.org/W2111550316","https://openalex.org/W2114010348","https://openalex.org/W2123771434","https://openalex.org/W2123808477","https://openalex.org/W2126143605","https://openalex.org/W2130290868","https://openalex.org/W2130466720","https://openalex.org/W2157412983","https://openalex.org/W2284628133","https://openalex.org/W2294246205","https://openalex.org/W2398071208","https://openalex.org/W2408526116","https://openalex.org/W2471520273","https://openalex.org/W2507912506","https://openalex.org/W2518172956","https://openalex.org/W2518312472","https://openalex.org/W2519091744","https://openalex.org/W2747921929","https://openalex.org/W2755348046","https://openalex.org/W2802935216","https://openalex.org/W2915960560","https://openalex.org/W2949382160","https://openalex.org/W2963454111","https://openalex.org/W2963609956","https://openalex.org/W6601527497","https://openalex.org/W6603838645","https://openalex.org/W6629815555","https://openalex.org/W6632366324","https://openalex.org/W6634053973","https://openalex.org/W6675401909","https://openalex.org/W6677973343","https://openalex.org/W6714062273","https://openalex.org/W6739879593","https://openalex.org/W6743951743"],"related_works":["https://openalex.org/W2482180524","https://openalex.org/W2748879498","https://openalex.org/W2772686614","https://openalex.org/W2902064555","https://openalex.org/W2755348046","https://openalex.org/W4311833917","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2408526116","https://openalex.org/W2482338111"],"abstract_inverted_index":{"The":[0,141,207],"most":[1],"prevalent":[2],"multilingual":[3],"Text-to-Speech":[4],"(TTS)":[5],"synthesis":[6],"systems":[7],"encounter":[8],"an":[9,183,225],"unnatural":[10],"speaker":[11,61],"shift":[12],"at":[13],"the":[14,29,33,102,119,179,187,203,214],"language":[15,63],"boundaries.":[16],"This":[17],"is":[18,38,70,84,217],"observed":[19],"when":[20,86],"they":[21],"are":[22],"employed":[23],"for":[24,115,138,199],"code-mixed":[25],"TTS":[26],"synthesis.":[27],"For":[28],"very":[30],"fact":[31],"that":[32,213],"collection":[34],"of":[35,54,80,94,97,154,158,174,192,220],"polyglot":[36],"speech":[37,58],"non-trivial,":[39],"many":[40],"alternative":[41],"approaches":[42],"have":[43],"been":[44,52],"in":[45,67,148,178],"focus.":[46],"Cross-Lingual":[47],"Voice":[48,90],"Conversion":[49,91],"(CLVC)":[50],"has":[51],"one":[53],"those":[55],"to":[56,71,88,185],"generate":[57],"with":[59,131,224],"desired":[60],"and":[62,104,117,123,151,162,166,190,205,209],"identities.":[64],"Our":[65],"aim":[66],"this":[68,139],"paper":[69],"design":[72],"a":[73,78,112,127,132,159,175,196,222],"light-weighted":[74],"CLVC":[75,83,116,223],"framework":[76],"between":[77,121,202],"pair":[79],"Mandarin-English":[81],"speakers.":[82,106],"challenging":[85],"compared":[87],"traditional":[89,197],"(VC)":[92],"because":[93],"its":[95],"nature":[96],"accommodating":[98],"unaligned":[99],"corpus":[100,114,161],"from":[101],"source":[103,188,204],"target":[105],"We":[107,125,170],"thus":[108],"focus":[109],"on":[110],"generating":[111],"parallel":[113,160,193],"bridging":[118],"gap":[120],"speakers":[122],"languages.":[124],"perform":[126],"text-independent":[128],"voice":[129],"conversion":[130,152],"three-layered":[133],"conventional":[134],"Neural":[135,176],"Network":[136,177],"(NN)":[137],"purpose.":[140],"main":[142],"contributions":[143],"include":[144],"i)":[145,182],"Source":[146],"similarity":[147,189],"both":[149],"training":[150],"stages":[153],"CLVC,":[155],"ii)":[156,195],"generation":[157,191],"iii)":[163],"text":[164],"independent":[165],"transcription":[167],"free":[168],"CLVC.":[169],"exploit":[171],"two":[172],"variants":[173],"proposed":[180,215],"framework,":[181],"autoencoder":[184],"enable":[186],"corpus,":[194],"DNN":[198],"feature":[200],"mapping":[201],"target.":[206],"subjective":[208],"objective":[210],"evaluations":[211],"show":[212],"method":[216],"indeed":[218],"capable":[219],"performing":[221],"auto-encoded":[226],"speech.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}