{"id":"https://openalex.org/W2972530081","doi":"https://doi.org/10.21437/ssw.2019-15","title":"Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion","display_name":"Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2972530081","doi":"https://doi.org/10.21437/ssw.2019-15","mag":"2972530081"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-15","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-15","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","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/A5067324900","display_name":"Tobias Gburrek","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tobias Gburrek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034662562","display_name":"Thomas Glarner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Glarner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055580486","display_name":"Janek Ebbers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janek Ebbers","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070024202","display_name":"Petra Wagner","orcid":"https://orcid.org/0000-0001-6662-3612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petra Wagner","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067324900"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2886,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67004123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9962000250816345,"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":0.8319224715232849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7462417483329773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7051112651824951},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6922634243965149},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5338384509086609},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5201335549354553},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5018975734710693},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49149882793426514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44767463207244873},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4348078966140747},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4292008578777313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3640565872192383},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25044721364974976}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8319224715232849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462417483329773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7051112651824951},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6922634243965149},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5338384509086609},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5201335549354553},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5018975734710693},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49149882793426514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44767463207244873},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4348078966140747},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4292008578777313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3640565872192383},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25044721364974976},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2019-15","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-15","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},{"id":"pmh:oai:pub.uni-bielefeld.de:2936382","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2936382","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1977362459","https://openalex.org/W2086796102","https://openalex.org/W2118850452","https://openalex.org/W2152974894","https://openalex.org/W2532494225","https://openalex.org/W2560512785","https://openalex.org/W2753738274","https://openalex.org/W2949382160","https://openalex.org/W2963539064","https://openalex.org/W2963618559","https://openalex.org/W2963799213"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2988134182"],"abstract_inverted_index":{"Gburrek":[0],"T,":[1],"Ebbers":[2],"J,":[3],"H\u00e4b-Umbach":[4],"R,":[5],"Wagner":[6],"P.":[7],"Unsupervised":[8],"Learning":[9],"of":[10,20],"a":[11],"Disentangled":[12],"Speech":[13,23],"Representation":[14],"for":[15],"Voice":[16],"Conversion.":[17],"In:":[18],"&lt;em&gt;Proceedings":[19],"the":[21],"10":[22],"Synthesis":[24],"Workshop":[25],"(SSW10)&lt;/em&gt;.":[26],"2019.":[27]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
