{"id":"https://openalex.org/W2579158309","doi":"https://doi.org/10.1109/apsipa.2016.7820716","title":"Deep neural network based voice conversion with a large synthesized parallel corpus","display_name":"Deep neural network based voice conversion with a large synthesized parallel corpus","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2579158309","doi":"https://doi.org/10.1109/apsipa.2016.7820716","mag":"2579158309"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2016.7820716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012954193","display_name":"Kehuang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kehuang Li","raw_affiliation_strings":["School of ECE, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of ECE, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9980999827384949,"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/naturalness","display_name":"Naturalness","score":0.8153406381607056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008322715759277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7159966230392456},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.6515074968338013},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5535111427307129},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5022976398468018},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5019733905792236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49346840381622314},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4874844551086426},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44406700134277344},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.43592801690101624},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4123968183994293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3564976453781128}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8153406381607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008322715759277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7159966230392456},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.6515074968338013},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5535111427307129},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5022976398468018},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5019733905792236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49346840381622314},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4874844551086426},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44406700134277344},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.43592801690101624},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4123968183994293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3564976453781128},{"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/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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2016.7820716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"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":41,"referenced_works":["https://openalex.org/W152891837","https://openalex.org/W173821756","https://openalex.org/W1963778986","https://openalex.org/W2013996527","https://openalex.org/W2033516035","https://openalex.org/W2044893557","https://openalex.org/W2046566646","https://openalex.org/W2049686551","https://openalex.org/W2055910046","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2100495367","https://openalex.org/W2105160541","https://openalex.org/W2105698384","https://openalex.org/W2111550316","https://openalex.org/W2114543868","https://openalex.org/W2120605154","https://openalex.org/W2121973264","https://openalex.org/W2125838338","https://openalex.org/W2129142580","https://openalex.org/W2135832479","https://openalex.org/W2136922672","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2156794882","https://openalex.org/W2157412983","https://openalex.org/W2160815625","https://openalex.org/W2294246205","https://openalex.org/W2294351487","https://openalex.org/W2401544731","https://openalex.org/W2407907561","https://openalex.org/W3177989406","https://openalex.org/W6606230598","https://openalex.org/W6607148522","https://openalex.org/W6662018355","https://openalex.org/W6672305501","https://openalex.org/W6696767757","https://openalex.org/W6697270646","https://openalex.org/W6713064456","https://openalex.org/W6713762797"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W290673751","https://openalex.org/W2017702615","https://openalex.org/W2024201202","https://openalex.org/W2370805772","https://openalex.org/W2537466733"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,12,16,27,36,53,61,67,94,105],"voice":[3],"conversion":[4],"framework":[5],"to":[6,15,26,51,64],"map":[7],"the":[8,31,77,86,90,118,122,129,133],"speech":[9,43,95,106,120,131],"features":[10],"of":[11,30,38,99,110],"source":[13,39],"speaker":[14,18],"target":[17,41],"based":[19],"on":[20],"deep":[21],"neural":[22],"networks":[23],"(DNNs).":[24],"Due":[25],"limited":[28],"availability":[29],"parallel":[32,55,92,124,135],"data":[33],"needed":[34],"for":[35,57,117],"pair":[37],"and":[40,45,104],"speakers,":[42],"synthesis":[44],"dynamic":[46],"time":[47],"warping":[48],"are":[49,115],"utilized":[50],"construct":[52],"large":[54,123],"corpus":[56,63,125],"DNN":[58],"training.":[59],"With":[60,89],"small":[62,134],"train":[65],"DNNs,":[66],"lower":[68],"log":[69],"spectral":[70],"distortion":[71],"can":[72],"still":[73],"be":[74],"seen":[75],"over":[76],"conventional":[78],"Gaussian":[79],"mixture":[80],"model":[81],"(GMM)":[82],"approach,":[83],"trained":[84],"with":[85,128],"same":[87],"data.":[88],"synthesized":[91],"corpus,":[93],"naturalness":[96],"preference":[97,108],"score":[98,109],"about":[100,111],"54.5%":[101],"vs.":[102,113],"32.8%":[103],"similarity":[107],"52.5%":[112],"23.6%":[114],"observed":[116],"DNN-converted":[119,130],"from":[121,132],"when":[126],"compared":[127],"corpus.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}