{"id":"https://openalex.org/W2937020545","doi":"https://doi.org/10.1109/icassp.2019.8683204","title":"Adversarially Trained Autoencoders for Parallel-data-free Voice Conversion","display_name":"Adversarially Trained Autoencoders for Parallel-data-free Voice Conversion","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937020545","doi":"https://doi.org/10.1109/icassp.2019.8683204","mag":"2937020545"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025069529","display_name":"Orhan \u00d6\u00e7al","orcid":"https://orcid.org/0000-0003-3835-283X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Orhan Ocal","raw_affiliation_strings":["Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111953908","display_name":"O\u011fuz H. Elibol","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oguz H. Elibol","raw_affiliation_strings":["Intel AI Lab, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Intel AI Lab, Santa Clara, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026246923","display_name":"Gokce Keskin","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokce Keskin","raw_affiliation_strings":["Intel AI Lab, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Intel AI Lab, Santa Clara, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080560015","display_name":"Cory Stephenson","orcid":"https://orcid.org/0000-0003-0078-6501"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cory Stephenson","raw_affiliation_strings":["Intel AI Lab, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Intel AI Lab, Santa Clara, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019478468","display_name":"Anil Thomas","orcid":"https://orcid.org/0000-0002-0774-2512"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anil Thomas","raw_affiliation_strings":["Intel AI Lab, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Intel AI Lab, Santa Clara, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030620564","display_name":"Kannan Ramchandran","orcid":"https://orcid.org/0000-0002-4567-328X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kannan Ramchandran","raw_affiliation_strings":["Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025069529"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.1201,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83357877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2777","last_page":"2781"},"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":0.9995999932289124,"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":0.9945999979972839,"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":0.9146261811256409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8274368643760681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7576283812522888},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.707160472869873},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6535558700561523},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.619278609752655},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5277802348136902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5219345092773438},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4871942400932312},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39637115597724915},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27720290422439575}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9146261811256409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274368643760681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7576283812522888},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.707160472869873},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6535558700561523},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.619278609752655},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5277802348136902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5219345092773438},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4871942400932312},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39637115597724915},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27720290422439575},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2099471712","https://openalex.org/W2102409316","https://openalex.org/W2120605154","https://openalex.org/W2120847449","https://openalex.org/W2141708418","https://openalex.org/W2156142001","https://openalex.org/W2527729766","https://openalex.org/W2603777577","https://openalex.org/W2619368999","https://openalex.org/W2768959015","https://openalex.org/W2774848319","https://openalex.org/W2783047733","https://openalex.org/W2803963372","https://openalex.org/W2962793481","https://openalex.org/W2963233633","https://openalex.org/W2963330667","https://openalex.org/W2963609956","https://openalex.org/W3189092450","https://openalex.org/W4231951313","https://openalex.org/W4320013936","https://openalex.org/W6675401909","https://openalex.org/W6738277540","https://openalex.org/W6745992979","https://openalex.org/W6746801104","https://openalex.org/W6747837047","https://openalex.org/W6752096078"],"related_works":["https://openalex.org/W4321789545","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W2946768379","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W4286910063","https://openalex.org/W2163707935","https://openalex.org/W83146503"],"abstract_inverted_index":{"We":[0,119],"present":[1,120],"a":[2,9,25,99],"method":[3,14,103],"for":[4],"converting":[5,107],"the":[6,55,58,67,72,80,84,96,108,116,124],"voices":[7],"between":[8],"set":[10],"of":[11,40,57,66,98,110,126],"speakers.":[12],"Our":[13],"is":[15,24,45,69],"based":[16],"on":[17],"training":[18,65,117],"multiple":[19,30],"autoencoder":[20],"paths,":[21],"where":[22],"there":[23],"single":[26,100],"speaker-independent":[27],"encoder":[28,59],"and":[29],"speaker-dependent":[31],"decoders.":[32],"The":[33,64],"autoencoders":[34],"are":[35],"trained":[36],"with":[37],"an":[38,41,48],"addition":[39],"adversarial":[42],"loss":[43],"which":[44],"provided":[46],"by":[47],"auxiliary":[49],"classifier":[50],"in":[51,71,115],"order":[52],"to":[53,60,95,106,113],"guide":[54],"output":[56],"be":[61],"speaker":[62],"independent.":[63],"model":[68],"unsupervised":[70],"sense":[73],"that":[74],"it":[75,88],"does":[76,87],"not":[77],"require":[78,89],"collecting":[79],"same":[81],"utterances":[82],"from":[83],"speakers":[85,112,114],"nor":[86],"time":[90],"aligning":[91],"over":[92],"phonemes.":[93],"Due":[94],"use":[97],"encoder,":[101],"our":[102,127],"can":[104],"generalize":[105],"voice":[109],"out-of-training":[111],"dataset.":[118],"subjective":[121],"tests":[122],"corroborating":[123],"performance":[125],"method.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}