{"id":"https://openalex.org/W2889516184","doi":"https://doi.org/10.21437/interspeech.2018-1598","title":"Acoustic Modeling Using Adversarially Trained Variational Recurrent Neural Network for Speech Synthesis","display_name":"Acoustic Modeling Using Adversarially Trained Variational Recurrent Neural Network for Speech Synthesis","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889516184","doi":"https://doi.org/10.21437/interspeech.2018-1598","mag":"2889516184"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5042018167","display_name":"Joun Yeop Lee","orcid":"https://orcid.org/0000-0002-3316-4808"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joun Yeop Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005088101","display_name":"Sung Jun Cheon","orcid":"https://orcid.org/0000-0002-7293-6997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sung Jun Cheon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424423","display_name":"Byoung Jin Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5104035145","display_name":"Eunwoo Song","orcid":"https://orcid.org/0000-0003-0642-7083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunwoo Song","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042018167"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.829,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.73796826,"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":"917","last_page":"921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.9962999820709229,"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":0.665414571762085},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6457898616790771},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5152602195739746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5088553428649902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.381030410528183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665414571762085},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6457898616790771},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5152602195739746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5088553428649902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.381030410528183}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/186836","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/186836","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W592244745","https://openalex.org/W1924770834","https://openalex.org/W1926768285","https://openalex.org/W2079735306","https://openalex.org/W2099471712","https://openalex.org/W2411541852","https://openalex.org/W2964060510","https://openalex.org/W2964167449"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212"],"abstract_inverted_index":{"In":[0,20,84],"this":[1,85],"paper,":[2],"we":[3,87,114],"propose":[4,88],"a":[5],"variational":[6,91],"recurrent":[7,47,92,138],"neural":[8,48,93],"network":[9,94],"(VRNN)":[10],"based":[11,156],"method":[12,157],"for":[13,107,130,145],"modeling":[14,55,109],"and":[15],"generating":[16],"speech":[17,26,106,111,146],"parameter":[18],"sequences.":[19],"recent":[21],"years.":[22],"the":[23,42,63,74,102,131,135,153,161],"performance":[24],"of":[25,66,77,104,143],"synthesis":[27,147],"systems":[28],"has":[29,51],"been":[30,52],"improved":[31],"over":[32],"conventional":[33,136,162],"techniques":[34],"thanks":[35],"to":[36,62,99,122],"deep":[37,44],"learning-based":[38],"acoustic":[39,108],"models.":[40],"Among":[41],"popular":[43],"learning":[45,117],"techniques,":[46],"networks":[49],"(RNNs)":[50],"successful":[53],"in":[54,110,119],"time-dependent":[56],"sequential":[57],"data":[58],"efficiently.":[59],"However,":[60],"due":[61],"deterministic":[64],"nature":[65],"RNNs":[67],"prediction,":[68],"such":[69],"models":[70],"do":[71],"not":[72],"reflect":[73],"full":[75],"complexity":[76],"highly":[78],"structured":[79],"data,":[80],"like":[81],"natural":[82,105],"speech.":[83],"regard,":[86],"adversarially":[89],"trained":[90],"(AdVRNN)":[95],"which":[96,140],"use":[97],"VRNN":[98,133],"better":[100,159],"represent":[101],"variability":[103],"synthesis.":[112],"Also,":[113],"apply":[115],"adversarial":[116],"scheme":[118],"training":[120],"AdVRNN":[121,155],"overcome":[123],"oversmoothing":[124],"problem.":[125],"We":[126],"conducted":[127],"comparative":[128],"experiments":[129],"proposed":[132,154],"with":[134],"gated":[137],"unit":[139],"is":[141,150],"one":[142],"RNNs,":[144],"system.":[148],"It":[149],"shown":[151],"that":[152],"performed":[158],"than":[160],"GRU":[163],"technique.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}