{"id":"https://openalex.org/W2944787681","doi":"https://doi.org/10.1109/iscslp.2018.8706574","title":"GTDNN-Based Voice Conversion Using DAEs with Binary Distributed Hidden Units","display_name":"GTDNN-Based Voice Conversion Using DAEs with Binary Distributed Hidden Units","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944787681","doi":"https://doi.org/10.1109/iscslp.2018.8706574","mag":"2944787681"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th 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/A5064846647","display_name":"Yiyang Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi-Yang Ding","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059516164","display_name":"Ya-Jun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Jun Hu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064846647"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21507855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"313","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":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.7788880467414856},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.699367105960846},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6358237266540527},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6022516489028931},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5941686630249023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5938358902931213},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.5805055499076843},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5801898837089539},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5678008794784546},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5675013065338135},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49793386459350586},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43730223178863525},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42509403824806213},{"id":"https://openalex.org/keywords/bernoullis-principle","display_name":"Bernoulli's principle","score":0.4200056791305542},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09354197978973389},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08691516518592834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788880467414856},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.699367105960846},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6358237266540527},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6022516489028931},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5941686630249023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938358902931213},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.5805055499076843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5801898837089539},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5678008794784546},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5675013065338135},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49793386459350586},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43730223178863525},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42509403824806213},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.4200056791305542},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09354197978973389},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08691516518592834},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/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/iscslp.2018.8706574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W2009272428","https://openalex.org/W2010833326","https://openalex.org/W2056852181","https://openalex.org/W2095425517","https://openalex.org/W2096555739","https://openalex.org/W2100495367","https://openalex.org/W2116064496","https://openalex.org/W2120605154","https://openalex.org/W2126143605","https://openalex.org/W2128123288","https://openalex.org/W2154920538","https://openalex.org/W2395849284","https://openalex.org/W2400679416","https://openalex.org/W2401544731","https://openalex.org/W2407907561","https://openalex.org/W2608305796","https://openalex.org/W2783657448","https://openalex.org/W2913932916","https://openalex.org/W6713064456","https://openalex.org/W6713111209","https://openalex.org/W6713762797","https://openalex.org/W6736620556"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W4387098302","https://openalex.org/W2803954745","https://openalex.org/W1829305295","https://openalex.org/W2593501769"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,50,69,95,144],"method":[4],"that":[5,113],"adopts":[6],"deep":[7,83,89],"autoencoders":[8,90],"with":[9,75],"binary":[10],"distributed":[11],"hidden":[12,107],"units":[13],"(BDAE)":[14],"as":[15,82],"feature":[16,58],"extractors":[17],"in":[18],"generatively":[19],"trained":[20],"DNNs":[21],"(GTDNN)":[22],"for":[23,57,71,140,151],"voice":[24,72],"conversion":[25],"(VC).":[26],"In":[27],"this":[28],"method,":[29],"the":[30,42,61,102,114,127,137,149],"source":[31,152],"and":[32,41,87,101,121,131],"target":[33,141],"speakers":[34],"are":[35,46,65],"modeled":[36],"separately":[37],"by":[38],"two":[39],"BDAEs,":[40],"extracted":[43],"high-level":[44],"features":[45,79],"used":[47],"to":[48,67],"train":[49],"Bernoulli":[51],"bi-directional":[52],"associated":[53],"memory":[54],"network":[55],"(BBAM)":[56],"mapping.":[59],"Then,":[60],"estimated":[62],"model":[63,139],"parameters":[64],"copied":[66],"construct":[68],"DNN":[70],"conversion.":[73],"Compared":[74],"other":[76],"neural":[77],"network-based":[78],"extractors,":[80],"such":[81],"belief":[84],"networks":[85],"(DBN)":[86],"conventional":[88,132],"(DAE),":[91],"BDAEs":[92,117],"can":[93],"obtain":[94],"better":[96,119],"balance":[97],"between":[98],"reconstruction":[99],"error":[100],"degree":[103],"of":[104,106,123],"binarization":[105],"units.":[108],"Our":[109],"experimental":[110],"results":[111],"show":[112,136],"GTDNN":[115],"using":[116,129],"achieved":[118],"naturalness":[120],"similarity":[122],"converted":[124],"speech":[125],"than":[126,148],"ones":[128],"DBNs":[130],"DAEs.":[133],"Further":[134],"experiments":[135],"BDAE":[138],"speaker":[142],"played":[143],"more":[145],"important":[146],"role":[147],"one":[150],"speaker.":[153]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}