{"id":"https://openalex.org/W4319781964","doi":"https://doi.org/10.1109/iscslp57327.2022.10038137","title":"A New Spoken Language Teaching Tech: Combining Multi-attention and AdaIN for One-shot Cross Language Voice Conversion","display_name":"A New Spoken Language Teaching Tech: Combining Multi-attention and AdaIN for One-shot Cross Language Voice Conversion","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319781964","doi":"https://doi.org/10.1109/iscslp57327.2022.10038137"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038137","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001927761","display_name":"Wenhan Yao","orcid":"https://orcid.org/0000-0003-1014-9565"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Yao","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076551862","display_name":"Ruixin Hu","orcid":"https://orcid.org/0000-0002-0999-0712"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixin Hu","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068030070","display_name":"Liangjie Huang","orcid":"https://orcid.org/0000-0003-0770-1582"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangjie Huang","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057554364","display_name":"Qi Luo","orcid":"https://orcid.org/0009-0000-8290-5441"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Luo","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005711805","display_name":"Wentao Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Shu","raw_affiliation_strings":["Beijing Language and Culture University"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102845007"],"corresponding_institution_ids":["https://openalex.org/I115212828"],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4619694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9891999959945679,"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":0.9886999726295471,"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":0.9077365398406982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8341981172561646},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5636629462242126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5231094360351562},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4711044430732727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4439714252948761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43612197041511536},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4102354049682617},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1434430480003357}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9077365398406982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341981172561646},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5636629462242126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5231094360351562},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4711044430732727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4439714252948761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43612197041511536},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4102354049682617},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1434430480003357},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/iscslp57327.2022.10038137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038137","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1588037970","https://openalex.org/W2517513811","https://openalex.org/W2532926524","https://openalex.org/W2600713714","https://openalex.org/W2603777577","https://openalex.org/W2617044865","https://openalex.org/W2752796333","https://openalex.org/W2897353073","https://openalex.org/W2937020545","https://openalex.org/W2937579788","https://openalex.org/W2963799213","https://openalex.org/W2972394484","https://openalex.org/W2972544500","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3096524539","https://openalex.org/W3097777922","https://openalex.org/W3099078140","https://openalex.org/W3162879338","https://openalex.org/W3197659778","https://openalex.org/W3198034710","https://openalex.org/W3198082505","https://openalex.org/W3217272406","https://openalex.org/W4224309976","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6783867762","https://openalex.org/W6785090365","https://openalex.org/W6804413408","https://openalex.org/W6810889627"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W2197967814"],"abstract_inverted_index":{"Computer":[0],"aided":[1],"pronunciation":[2,24,52],"training(CAPT)":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,96,104],"oral":[9,18],"language":[10,70],"teaching.":[11],"The":[12],"main":[13],"methods":[14],"of":[15,60],"traditional":[16],"computer-assisted":[17],"teaching":[19],"include":[20],"mispronunciation":[21],"detection":[22],"and":[23,26,82,99,115,132],"scoring":[25],"assessment.However,":[27],"these":[28,54],"two":[29,55],"techniques":[30],"only":[31],"give":[32],"negative":[33],"feedback":[34],"information":[35],"such":[36],"as":[37],"scores":[38],"or":[39],"error":[40],"categories.":[41],"In":[42],"this":[43,64,137],"case,it":[44],"is":[45],"difficult":[46],"for":[47],"learners":[48],"to":[49,121],"refine":[50],"their":[51],"through":[53],"indicators":[56],"without":[57],"the":[58,88,97,101,112,130,141],"guidance":[59],"correct":[61],"speech.To":[62],"tackle":[63],"problem,":[65],"we":[66],"proposed":[67],"a":[68],"cross":[69],"voice":[71],"conversion(VC)":[72],"framework":[73,124],"that":[74,136],"can":[75,86,110],"generate":[76],"speech":[77,80],"with":[78],"template":[79],"content":[81],"learners\u2019":[83],"own":[84],"timbre,which":[85],"guide":[87],"learner\u2019s":[89],"pronunciation.To":[90],"improve":[91,111],"VC":[92,123],"effect,we":[93],"apply":[94],"AdaIN":[95],"fore-end":[98],"after":[100],"Value":[102],"matrix":[103],"multi-head":[105],"attention":[106],"once":[107],"respectively,called":[108],"attention-AdaIN,which":[109],"style":[113],"transfer":[114],"sequence":[116],"generation":[117],"ability.We":[118],"used":[119],"attention-AdaIN":[120],"construct":[122],"based":[125],"on":[126,129],"VAE.Experiments":[127],"conducted":[128],"AISHELL-3":[131],"VCTK":[133],"corpus":[134],"showed":[135],"new":[138],"aprroach":[139],"improved":[140],"baseline":[142],"VAE-VC.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}