{"id":"https://openalex.org/W4297841435","doi":"https://doi.org/10.21437/interspeech.2022-10740","title":"Investigation into Target Speaking Rate Adaptation for Voice Conversion","display_name":"Investigation into Target Speaking Rate Adaptation for Voice Conversion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841435","doi":"https://doi.org/10.21437/interspeech.2022-10740"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10740","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5009710583","display_name":"Michael Kuhlmann","orcid":"https://orcid.org/0000-0003-3664-6922"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Kuhlmann","raw_affiliation_strings":["Paderborn University, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022762565","display_name":"Fritz Seebauer","orcid":null},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fritz Seebauer","raw_affiliation_strings":["Bielefeld University, Germany"],"affiliations":[{"raw_affiliation_string":"Bielefeld University, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055580486","display_name":"Janek Ebbers","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Janek Ebbers","raw_affiliation_strings":["Paderborn University, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070024202","display_name":"Petra Wagner","orcid":"https://orcid.org/0000-0001-6662-3612"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Petra Wagner","raw_affiliation_strings":["Bielefeld University, Germany"],"affiliations":[{"raw_affiliation_string":"Bielefeld University, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070024202"],"corresponding_institution_ids":["https://openalex.org/I20121455"],"apc_list":null,"apc_paid":null,"fwci":0.5194,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6352618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9535999894142151,"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":0.9535999894142151,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6441358923912048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6059424877166748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5651667714118958},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0966632068157196},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06806904077529907}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6441358923912048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6059424877166748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5651667714118958},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0966632068157196},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06806904077529907}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10740","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1518481329","https://openalex.org/W1959608418","https://openalex.org/W2065722210","https://openalex.org/W2099621636","https://openalex.org/W2125001590","https://openalex.org/W2168510624","https://openalex.org/W2399934308","https://openalex.org/W2403729239","https://openalex.org/W2502312327","https://openalex.org/W2747874407","https://openalex.org/W2945478979","https://openalex.org/W2962780374","https://openalex.org/W2963830550","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3096524539","https://openalex.org/W3096656254","https://openalex.org/W3098557217","https://openalex.org/W3162390194","https://openalex.org/W3162517041","https://openalex.org/W3163475957","https://openalex.org/W3168292814","https://openalex.org/W3169739675","https://openalex.org/W3198082505","https://openalex.org/W3202871751","https://openalex.org/W4210633887","https://openalex.org/W4225892118","https://openalex.org/W4289299319","https://openalex.org/W4296068414","https://openalex.org/W4297808394","https://openalex.org/W4301371414","https://openalex.org/W4390912360"],"related_works":["https://openalex.org/W1571518467","https://openalex.org/W87991986","https://openalex.org/W2020291234","https://openalex.org/W2094520212","https://openalex.org/W2001850503","https://openalex.org/W2368779261","https://openalex.org/W1576801573","https://openalex.org/W2778699561","https://openalex.org/W2017762168","https://openalex.org/W2370281303"],"abstract_inverted_index":{"Disentangling":[0],"speaker":[1,21,85,160],"and":[2,36,67,109,123,134,140,152,161],"content":[3,17,68,135],"attributes":[4],"of":[5,49,78,100,148],"a":[6,24,61,149,158],"speech":[7,38,150],"signal":[8],"into":[9],"separate":[10],"latent":[11],"representations":[12],"followed":[13],"by":[14],"decoding":[15],"the":[16,79,83,93,98,146,154,164,170,177],"with":[18,34,174],"an":[19,76,107],"exchanged":[20],"representation":[22,121],"is":[23,56,103],"popular":[25],"approach":[26],"for":[27,120],"voice":[28,65,132],"conversion,":[29],"which":[30,114],"can":[31],"be":[32],"trained":[33],"non-parallel":[35],"unlabeled":[37],"data.However,":[39],"previous":[40,70],"approaches":[41,142],"perform":[42],"disentanglement":[43,112],"only":[44,117],"implicitly":[45],"via":[46],"some":[47,89],"sort":[48],"information":[50],"bottleneck":[51],"or":[52,86,95],"normalization,":[53],"where":[54],"it":[55,126],"usually":[57,72],"hard":[58],"to":[59,82,92,128,143,157,168,176],"find":[60],"good":[62],"trade-off":[63],"between":[64],"conversion":[66,133],"reconstruction.Further,":[69],"works":[71],"do":[73],"not":[74],"consider":[75],"adaptation":[77,166],"speaking":[80,155,171],"rate":[81,172],"target":[84,159,178],"they":[87],"put":[88],"major":[90],"restrictions":[91],"data":[94],"use":[96],"case.Therefore,":[97],"contribution":[99],"this":[101],"work":[102],"two-fold.First,":[104],"we":[105,137],"employ":[106],"explicit":[108],"fully":[110],"unsupervised":[111],"approach,":[113],"has":[115],"previously":[116],"been":[118],"used":[119],"learning,":[122],"show":[124,162],"that":[125,163],"allows":[127,167],"obtain":[129],"both":[130],"superior":[131],"reconstruction.Second,":[136],"investigate":[138],"simple":[139],"generic":[141],"linearly":[144],"adapt":[145],"length":[147],"signal,":[151],"hence":[153],"rate,":[156],"proposed":[165],"increase":[169],"similarity":[173],"respect":[175],"speaker.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}