{"id":"https://openalex.org/W2901254300","doi":"https://doi.org/10.1109/icassp.2019.8682380","title":"Improving Sequence-to-sequence Voice Conversion by Adding Text-supervision","display_name":"Improving Sequence-to-sequence Voice Conversion by Adding Text-supervision","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2901254300","doi":"https://doi.org/10.1109/icassp.2019.8682380","mag":"2901254300"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682380","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.08111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073662121","display_name":"Jing-Xuan Zhang","orcid":"https://orcid.org/0000-0003-4341-3174"},"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":"middle","author":{"id":"https://openalex.org/A5064657549","display_name":"Yuan Jiang","orcid":"https://orcid.org/0000-0003-4307-0562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Jiang","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Co., Ltd., Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co., Ltd., Hefei, P.R.China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343775","display_name":"Lijuan Liu","orcid":"https://orcid.org/0000-0001-6804-848X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li-Juan Liu","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Co., Ltd., Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co., Ltd., Hefei, P.R.China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745497","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0003-3706-6479"},"institutions":[{"id":"https://openalex.org/I4210109416","display_name":"Anhui Science and Technology University","ror":"https://ror.org/01pn91c28","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210109416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Liang","raw_affiliation_strings":["Anhui Science and Technology Research Institute, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Science and Technology Research Institute, Hefei, P.R.China","institution_ids":["https://openalex.org/I4210109416"]}]},{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8426,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93221934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6785","last_page":"6789"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9937999844551086,"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/T10028","display_name":"Topic Modeling","score":0.9793000221252441,"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/naturalness","display_name":"Naturalness","score":0.8550152778625488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928062677383423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7356553077697754},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6365788578987122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6303683519363403},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6221952438354492},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6139820218086243},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46773678064346313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4608326554298401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45005887746810913},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4471818506717682},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08216893672943115}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8550152778625488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928062677383423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7356553077697754},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6365788578987122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6303683519363403},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6221952438354492},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6139820218086243},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46773678064346313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4608326554298401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45005887746810913},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4471818506717682},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08216893672943115},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682380","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"},{"id":"pmh:oai:arXiv.org:1811.08111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.08111","pdf_url":"https://arxiv.org/pdf/1811.08111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.08111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.08111","pdf_url":"https://arxiv.org/pdf/1811.08111","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1509691205","https://openalex.org/W1518567289","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W2049686551","https://openalex.org/W2086796102","https://openalex.org/W2094035326","https://openalex.org/W2117130368","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2135832479","https://openalex.org/W2157412983","https://openalex.org/W2494980014","https://openalex.org/W2519091744","https://openalex.org/W2576309025","https://openalex.org/W2603810172","https://openalex.org/W2755891984","https://openalex.org/W2775795276","https://openalex.org/W2949382160","https://openalex.org/W2963609956","https://openalex.org/W2963929654","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W3099078140","https://openalex.org/W4240592325","https://openalex.org/W4245885054","https://openalex.org/W6631129722","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6736996214","https://openalex.org/W6744261651","https://openalex.org/W6747218270","https://openalex.org/W6785635027"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"methods":[3],"of":[4,7,14,54,73,133,145],"making":[5],"using":[6],"text":[8,52,93],"supervision":[9],"to":[10,69,95,106],"improve":[11,46,142],"the":[12,26,51,70,74,121,131,143],"performance":[13,48,144],"sequence-to-sequence":[15],"(seq2seq)":[16],"voice":[17,23,135,147],"conversion.":[18,136],"Compared":[19],"with":[20,111,124],"conventional":[21],"frame-to-frame":[22],"conversion":[24,148],"approaches,":[25],"seq2seq":[27,75,134,146],"acoustic":[28],"modeling":[29],"method":[30,88,110,139],"proposed":[31,90,109],"in":[32],"our":[33,108],"previous":[34],"work":[35],"achieved":[36],"higher":[37],"naturalness":[38],"and":[39,77],"similarity.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"further":[45,141],"its":[47],"by":[49],"utilizing":[50],"transcriptions":[53],"parallel":[55,98],"training":[56,112,154],"data.":[57],"First,":[58],"a":[59,82,86],"multi-task":[60,122],"learning":[61,123],"structure":[62],"is":[63,89,127],"designed":[64],"which":[65,91],"adds":[66],"auxiliary":[67],"classifiers":[68],"middle":[71],"layers":[72],"model":[76,101],"predicts":[78],"linguistic":[79,125],"labels":[80,126],"as":[81],"secondary":[83],"task.":[84],"Second,":[85],"data-augmentation":[87,138],"utilizes":[92],"alignment":[94],"produce":[96],"extra":[97],"sequences":[99],"for":[100],"training.":[102],"Experiments":[103],"are":[104,156],"conducted":[105],"evaluate":[107],"sets":[113],"at":[114,129],"different":[115],"sizes.":[116],"Experimental":[117],"results":[118],"show":[119],"that":[120],"effective":[128],"reducing":[130],"errors":[132],"The":[137],"can":[140],"when":[149],"only":[150],"50":[151],"or":[152],"100":[153],"utterances":[155],"available.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2018-11-29T00:00:00"}