{"id":"https://openalex.org/W2407633780","doi":"https://doi.org/10.21437/interspeech.2015-118","title":"Semi-supervised training of a voice conversion mapping function using a joint-autoencoder","display_name":"Semi-supervised training of a voice conversion mapping function using a joint-autoencoder","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2407633780","doi":"https://doi.org/10.21437/interspeech.2015-118","mag":"2407633780"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-118","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5014830287","display_name":"Seyed Hamidreza Mohammadi","orcid":"https://orcid.org/0000-0002-6892-9241"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyed Hamidreza Mohammadi","raw_affiliation_strings":["Oregon Health & Science University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066668295","display_name":"Alexander Kain","orcid":"https://orcid.org/0000-0001-5807-9311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Kain","raw_affiliation_strings":["Institute on Development & Disability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute on Development & Disability","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0288,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79816337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"284","last_page":"288"},"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":0.9991999864578247,"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":0.998199999332428,"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/autoencoder","display_name":"Autoencoder","score":0.8793485164642334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103511333465576},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.702483594417572},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6321018934249878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5867192149162292},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.586349606513977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5601760745048523},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5460637807846069},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47478052973747253},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.43831580877304077},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4330287575721741},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39606863260269165},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11852076649665833}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8793485164642334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103511333465576},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.702483594417572},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6321018934249878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5867192149162292},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.586349606513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601760745048523},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5460637807846069},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47478052973747253},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.43831580877304077},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4330287575721741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39606863260269165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11852076649665833},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-118","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1509691205","https://openalex.org/W1518567289","https://openalex.org/W1533861849","https://openalex.org/W1635512741","https://openalex.org/W1972420736","https://openalex.org/W1972978214","https://openalex.org/W1993882792","https://openalex.org/W2009272428","https://openalex.org/W2010833326","https://openalex.org/W2020290924","https://openalex.org/W2029836932","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2095705004","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2125508626","https://openalex.org/W2138857742","https://openalex.org/W2141708418","https://openalex.org/W2145094598","https://openalex.org/W2157412983","https://openalex.org/W2161476805","https://openalex.org/W2244925781","https://openalex.org/W2294246205","https://openalex.org/W2294351487","https://openalex.org/W2396025094","https://openalex.org/W2401544731","https://openalex.org/W2404269151","https://openalex.org/W2407907561","https://openalex.org/W2619993508"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2389120450","https://openalex.org/W55249799"],"abstract_inverted_index":{"Recently,":[0],"researchers":[1],"have":[2,125],"begun":[3],"to":[4,30,62,72,117,182],"investigate":[5],"Deep":[6],"Neural":[7],"Network":[8],"(DNN)":[9],"architectures":[10],"as":[11],"mapping":[12,185],"functions":[13],"in":[14],"voice":[15],"conversion":[16,188],"systems.":[17],"In":[18],"this":[19,111],"study,":[20],"we":[21,124],"propose":[22,61],"a":[23,32,46,54],"novel":[24],"StackedJoint-Autoencoder":[25],"(SJAE)":[26],"architecture,":[27],"which":[28],"aims":[29],"find":[31],"common":[33],"encoding":[34],"of":[35,79,100,110,131,140,162,171,175],"parallel":[36],"source":[37,74,83],"and":[38,75,84,96,103,135,150,156,178],"target":[39,76,85],"features.":[40],"The":[41,87,108,166],"SJAE":[42,65],"is":[43,90],"initialized":[44],"from":[45,92],"Stacked-Autoencoder":[47],"(SAE)":[48],"that":[49,69,169],"has":[50],"been":[51],"trained":[52],"on":[53],"large":[55],"general-purpose":[56],"speech":[57],"database.":[58],"We":[59,145],"also":[60,136],"train":[63,146],"the":[64,73,82,93,97,101,128,132,137,160,172,184],"using":[66,80,106,179],"unrelated":[67,180],"speakers":[68,181],"are":[70],"similar":[71,141],"speaker,":[77],"instead":[78],"only":[81],"speakers.":[86],"final":[88],"DNN":[89],"constructed":[91],"source-encoding":[94],"part":[95,99],"target-decoding":[98],"SJAE,":[102,177],"then":[104],"fine-tuned":[105],"back-propagation.":[107],"use":[109,118],"semi-supervised":[112],"training":[113,164],"approach":[114],"allows":[115],"us":[116],"multiple":[119],"frames":[120],"during":[121],"mapping,":[122],"since":[123],"previously":[126],"learned":[127],"general":[129,138],"structure":[130,139],"acoustic":[133],"space":[134],"source-target":[142],"speaker":[143,148],"mappings.":[144],"two":[147],"conversions":[149],"compare":[151],"several":[152],"system":[153],"configurations":[154],"objectively":[155],"subjectively":[157],"while":[158],"varying":[159],"number":[161],"available":[163],"sentences.":[165],"results":[167],"show":[168],"each":[170],"individual":[173],"contributions":[174],"SAE,":[176],"initialize":[183],"function":[186],"increases":[187],"performance.":[189]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}