{"id":"https://openalex.org/W2007818064","doi":"https://doi.org/10.1587/transinf.2014edp7116","title":"Cross-Dialectal Voice Conversion with Neural Networks","display_name":"Cross-Dialectal Voice Conversion with Neural Networks","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2007818064","doi":"https://doi.org/10.1587/transinf.2014edp7116","mag":"2007818064"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2014edp7116","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7116","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/11/E97.D_2014EDP7116/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/11/E97.D_2014EDP7116/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100964048","display_name":"Weixun Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixun GAO","raw_affiliation_strings":["School of Information Science and Technology, Donghua Univeristy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Donghua Univeristy","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065024360","display_name":"Qiying Cao","orcid":"https://orcid.org/0000-0001-7976-6364"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiying CAO","raw_affiliation_strings":["College of Computer Science & Technology, Donghua Univeristy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science & Technology, Donghua Univeristy","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao QIAN","raw_affiliation_strings":["Speech Group of Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group of Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0723838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E97.D","issue":"11","first_page":"2872","last_page":"2880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9824000000953674,"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":0.9707000255584717,"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":0.8066433668136597},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6751357316970825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6599596738815308},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5881099104881287},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5583603978157043},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5556222200393677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5293800234794617},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5231903195381165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5079427361488342},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4434521496295929},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43379923701286316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14027217030525208},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08892777562141418},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08891308307647705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066433668136597},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6751357316970825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6599596738815308},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5881099104881287},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5583603978157043},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5556222200393677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5293800234794617},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5231903195381165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5079427361488342},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4434521496295929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43379923701286316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14027217030525208},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08892777562141418},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08891308307647705},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2014edp7116","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7116","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/11/E97.D_2014EDP7116/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2014edp7116","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7116","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/11/E97.D_2014EDP7116/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2007818064.pdf","grobid_xml":"https://content.openalex.org/works/W2007818064.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W3276882","https://openalex.org/W50577135","https://openalex.org/W217970951","https://openalex.org/W1498436455","https://openalex.org/W1972420736","https://openalex.org/W2006654546","https://openalex.org/W2033641795","https://openalex.org/W2049686551","https://openalex.org/W2076794394","https://openalex.org/W2108674328","https://openalex.org/W2111194146","https://openalex.org/W2120605154","https://openalex.org/W2136922672","https://openalex.org/W2138857742","https://openalex.org/W2141778357","https://openalex.org/W2144513243","https://openalex.org/W2147768505","https://openalex.org/W2150658333","https://openalex.org/W2152974894","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2294351487","https://openalex.org/W2295490460","https://openalex.org/W2401544731","https://openalex.org/W2403195671","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W2111961547"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"use":[4],"neural":[5],"networks":[6],"(NNs)":[7],"for":[8],"cross-dialectal":[9,107],"(Mandarin-Shanghainese)":[10],"voice":[11,108],"conversion":[12,109],"using":[13],"a":[14,21,70],"bi-dialectal":[15],"speakers'":[16],"recordings.":[17],"This":[18,48,116],"system":[19],"employs":[20],"nonlinear":[22],"mapping":[23],"function,":[24],"which":[25,57,66,88],"is":[26,58,110,118],"trained":[27],"by":[28],"parallel":[29],"mandarin":[30],"features":[31,42],"of":[32,45,106,114,125,150,169],"source":[33,39],"and":[34,84,92,98,135,144,156,174,181],"target":[35,46,182],"speakers,":[36],"to":[37,43,60,69,112],"convert":[38],"speaker's":[40],"Shanghainese":[41,172,179],"those":[44],"speaker.":[47],"study":[49],"investigates":[50],"three":[51],"training":[52,97,158],"aspects:":[53],"a)":[54],"Frequency":[55],"warping,":[56],"supposed":[59],"be":[61,78],"language":[62],"independent;":[63],"b)":[64],"Pre-training,":[65],"drives":[67],"weights":[68],"better":[71],"starting":[72],"point":[73],"than":[74],"random":[75],"initialization":[76],"or":[77],"regarded":[79],"as":[80],"unsupervised":[81],"feature":[82,129],"learning;":[83],"c)":[85],"Sequence":[86],"training,":[87],"minimizes":[89],"sequence-level":[90],"errors":[91],"matches":[93],"objectives":[94],"used":[95],"in":[96],"converting.":[99],"Experimental":[100],"results":[101],"show":[102,153],"that":[103,113,154],"the":[104,121,160,170,175],"performance":[105],"close":[111],"intra-dialectal.":[115],"benefit":[117],"likely":[119],"from":[120],"strong":[122],"learning":[123],"capabilities":[124],"NNs,":[126],"e.g.,":[127],"exploiting":[128],"correlations":[130],"between":[131,177],"fundamental":[132],"frequency":[133],"(F0)":[134],"spectrum.":[136],"The":[137,167],"objective":[138],"measures:":[139],"log":[140],"spectral":[141],"distortion":[142],"(LSD)":[143],"root":[145],"mean":[146,162],"squared":[147],"error":[148,164],"(RMSE)":[149],"F0,":[151],"both":[152],"pre-training":[155],"sequence":[157],"outperform":[159],"frame-level":[161],"square":[163],"(MSE)":[165],"training.":[166],"naturalness":[168],"converted":[171,178],"speech":[173,180,184],"similarity":[176],"Mandarin":[183],"are":[185],"significantly":[186],"improved.":[187]},"counts_by_year":[],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}