{"id":"https://openalex.org/W3046998876","doi":"https://doi.org/10.21437/interspeech.2020-36","title":"Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning","display_name":"Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3046998876","doi":"https://doi.org/10.21437/interspeech.2020-36","mag":"3046998876"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5100688796","display_name":"Jingxuan Zhang","orcid":"https://orcid.org/0009-0005-5770-1128"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing-Xuan Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"771","last_page":"775"},"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":0.9998000264167786,"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":0.9993000030517578,"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/adversarial-system","display_name":"Adversarial system","score":0.7831770777702332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7475596070289612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4775484502315521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41084814071655273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36996084451675415}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7831770777702332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475596070289612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4775484502315521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41084814071655273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36996084451675415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1579853615","https://openalex.org/W2009272428","https://openalex.org/W2049686551","https://openalex.org/W2099471712","https://openalex.org/W2100819376","https://openalex.org/W2126143605","https://openalex.org/W2157412983","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2576309025","https://openalex.org/W2608377413","https://openalex.org/W2739748921","https://openalex.org/W2888922217","https://openalex.org/W2889329491","https://openalex.org/W2899877258","https://openalex.org/W2937020545","https://openalex.org/W2939131199","https://openalex.org/W2962879692","https://openalex.org/W2963290645","https://openalex.org/W2963609956","https://openalex.org/W2963808252","https://openalex.org/W2963830550","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W3015805741","https://openalex.org/W3099078140","https://openalex.org/W3101689408","https://openalex.org/W4289299319","https://openalex.org/W4295521014","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W2482350142","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W3192589309"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"adversarial":[4,65,85],"learning":[5],"method":[6,120],"for":[7],"recognition-synthesis":[8],"based":[9],"non-parallel":[10],"voice":[11,46],"conversion.A":[12],"recognizer":[13,31],"is":[14,67,89,118],"used":[15,90],"to":[16,71,91],"transform":[17],"acoustic":[18],"features":[19,28,95],"into":[20],"linguistic":[21,44,74],"representations":[22,75],"while":[23],"a":[24,63,83,102,107],"synthesizer":[25],"recovers":[26],"output":[27],"from":[29,42,96],"the":[30,35,39,43,53,57,77,93,114,125,130],"outputs":[32],"together":[33],"with":[34,56],"speaker":[36,40,54,64,116],"identity.By":[37],"separating":[38],"characteristics":[41],"representations,":[45],"conversion":[47],"can":[48],"be":[49],"achieved":[50,121],"by":[51],"replacing":[52],"identity":[55],"target":[58],"one.In":[59],"our":[60],"proposed":[61],"method,":[62],"loss":[66,88],"adopted":[68],"in":[69,133],"order":[70],"obtain":[72],"speaker-independent":[73],"using":[76],"recognizer.Furthermore,":[78],"discriminators":[79],"are":[80],"introduced":[81],"and":[82,110],"generative":[84],"network":[86],"(GAN)":[87],"prevent":[92],"predicted":[94],"being":[97],"over-smoothed.For":[98],"training":[99],"model":[100,127],"parameters,":[101],"strategy":[103],"of":[104],"pre-training":[105],"on":[106,113],"multi-speaker":[108],"dataset":[109],"then":[111],"fine-tuning":[112],"source-target":[115],"pair":[117],"designed.Our":[119],"higher":[122],"similarity":[123],"than":[124],"baseline":[126],"that":[128],"obtained":[129],"best":[131],"performance":[132],"Voice":[134],"Conversion":[135],"Challenge":[136],"2018.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}