{"id":"https://openalex.org/W3132929045","doi":null,"title":"Personalized End-to-End Mandarin Speech Synthesis using Small-sized Corpus","display_name":"Personalized End-to-End Mandarin Speech Synthesis using Small-sized Corpus","publication_year":2020,"publication_date":"2020-12-07","ids":{"openalex":"https://openalex.org/W3132929045","mag":"3132929045"},"language":"en","primary_location":{"id":"mag:3132929045","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/apsipa/apsipa2020.html#YuanH20","pdf_url":null,"source":{"id":"https://openalex.org/S4363607812","display_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5034535852","display_name":"Chenhan Yuan","orcid":"https://orcid.org/0000-0001-9667-0460","observed_orcids":["https://orcid.org/0000-0001-9667-0460"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenhan Yuan","raw_affiliation_strings":["Virginia Tech,Dept. of Computer Science,Blacksburg,VA,USA,24060"],"raw_orcid":"https://orcid.org/0000-0001-9667-0460","affiliations":[{"raw_affiliation_string":"Virginia Tech,Dept. of Computer Science,Blacksburg,VA,USA,24060","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112612990","display_name":"Yi\u2010Chin Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1309796872","display_name":"National Pingtung University","ror":"https://ror.org/03z698x91","country_code":"TW","type":"education","lineage":["https://openalex.org/I1309796872"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi\u2010Chin Huang","raw_affiliation_strings":["National Pingtung University,Dept. of Computer Science,Pingtung,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Pingtung University,Dept. of Computer Science,Pingtung,Taiwan","institution_ids":["https://openalex.org/I1309796872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"837","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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":0.0,"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/personalized-speech-synthesis","display_name":"personalized speech synthesis","score":0.9679999947547913},{"id":"https://openalex.org/keywords/mandarin-speech-synthesis","display_name":"Mandarin speech synthesis","score":0.9290000200271606},{"id":"https://openalex.org/keywords/end-to-end-speech-synthesis","display_name":"end-to-end speech synthesis","score":0.8690000176429749},{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.8949999809265137},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.8420000076293945},{"id":"https://openalex.org/keywords/loudspeaker-modeling","display_name":"speaker modeling","score":0.41999998688697815},{"id":"https://openalex.org/keywords/timbre-modeling","display_name":"timbre modeling","score":0.7129999995231628},{"id":"https://openalex.org/keywords/speaker-identity","display_name":"speaker identity","score":0.503000020980835},{"id":"https://openalex.org/keywords/automatic-feature-extraction","display_name":"automatic feature extraction","score":0.4390000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395612835884094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6412161588668823},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5573585629463196},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5237909555435181},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5139762759208679},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46900081634521484},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45033153891563416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4463719129562378},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4434177875518799},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.43029534816741943},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4289698004722595},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42847999930381775},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37950795888900757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37047669291496277},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08417975902557373},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3132929045","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/apsipa/apsipa2020.html#YuanH20","pdf_url":null,"source":{"id":"https://openalex.org/S4363607812","display_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W204967857","https://openalex.org/W1634005169","https://openalex.org/W2081687495","https://openalex.org/W2130942839","https://openalex.org/W2132339004","https://openalex.org/W2139525902","https://openalex.org/W2153579005","https://openalex.org/W2171928131","https://openalex.org/W2251811146","https://openalex.org/W2471520273","https://openalex.org/W2474824677","https://openalex.org/W2530876040","https://openalex.org/W2532494225","https://openalex.org/W2554952599","https://openalex.org/W2749651610","https://openalex.org/W2898847420","https://openalex.org/W2962691331","https://openalex.org/W2963808252","https://openalex.org/W2964243274","https://openalex.org/W2971206239"],"related_works":["https://openalex.org/W4411172976","https://openalex.org/W2532494225","https://openalex.org/W2039241583","https://openalex.org/W4416143831","https://openalex.org/W3090528452","https://openalex.org/W4407904113","https://openalex.org/W2625545704","https://openalex.org/W3011028252","https://openalex.org/W2947445680","https://openalex.org/W3095755761"],"abstract_inverted_index":{"Conventionally,":[0],"voice":[1],"conversion":[2],"techniques":[3],"are":[4,28,53],"based":[5],"on":[6,113,135],"the":[7,16,20,24,33,36,48,73,83,89,94,105,114,124,130,137,147,160,176,190],"source-filter":[8],"model,":[9,127],"which":[10,111,133,151],"extracts":[11],"acoustic":[12,126],"features":[13],"and":[14,35,79,143,165,185],"transforms":[15],"spectrum":[17],"distribution":[18],"from":[19,146],"source":[21],"speaker":[22,144],"to":[23,31,42,46,55,75,81,117,153,156,195],"target.":[25],"Parallel":[26],"corpora":[27],"usually":[29],"required":[30],"learn":[32],"transformation":[34],"alignment":[37,164],"of":[38,93,162],"phone":[39],"units":[40],"has":[41],"be":[43,120,154,169],"done":[44],"manually":[45],"obtain":[47],"optimal":[49],"conversion.":[50],"These":[51],"requirements":[52],"hard":[54],"achieve":[56],"in":[57],"daily":[58],"use.":[59],"Therefore,":[60,159],"we":[61,128],"proposed":[62,177],"an":[63],"end-to-end":[64],"method":[65],"for":[66,123,181],"personalized":[67,125,182],"speech":[68,95,183],"synthesis":[69,184],"system":[70,178,192],"by":[71,97],"combining":[72],"ideas":[74],"tackle":[76],"these":[77],"problems":[78],"try":[80],"make":[82],"data":[84],"collection":[85],"task":[86],"attainable.We":[87],"integrated":[88],"linguistic/acoustic":[90],"feature":[91,108],"extraction":[92,109],"corpus":[96,167],"adopting":[98],"suitable":[99],"neural":[100],"networks.":[101],"In":[102],"this":[103],"way,":[104],"traditional":[106],"linguistic":[107],"module":[110],"relies":[112],"expert":[115],"knowledge":[116],"build":[118],"could":[119,168],"substituted.":[121],"Then,":[122],"adopted":[129],"variational":[131],"auto-encoder,":[132],"focused":[134],"separating":[136],"speaker-related":[138],"properties,":[139],"such":[140],"as":[141],"timbre":[142],"identity,":[145],"underlying":[148],"latent":[149],"code,":[150],"assumed":[152],"related":[155],"phoneme":[157],"identity.":[158],"requirement":[161],"manual":[163],"parallel":[166],"overcome.":[170],"Finally,":[171],"experimental":[172],"results":[173],"showed":[174],"that":[175],"indeed":[179],"useful":[180],"provides":[186],"comparable":[187],"performance":[188],"with":[189],"conventional":[191],"while":[193],"easier":[194],"build.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2021-03-01T00:00:00"}