{"id":"https://openalex.org/W3022057435","doi":"https://doi.org/10.1109/lsp.2020.3025410","title":"Adversarial Feature Learning and Unsupervised Clustering Based Speech Synthesis for Found Data With Acoustic and Textual Noise","display_name":"Adversarial Feature Learning and Unsupervised Clustering Based Speech Synthesis for Found Data With Acoustic and Textual Noise","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3022057435","doi":"https://doi.org/10.1109/lsp.2020.3025410","mag":"3022057435"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2020.3025410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3025410","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.13595","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shan Yang","raw_affiliation_strings":["School of Computer Science, and Engineering, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0003-4464-146X","affiliations":[{"raw_affiliation_string":"School of Computer Science, and Engineering, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuxuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Bytedance AI Lab, ByteDance, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, ByteDance, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, and Engineering, Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0001-8234-0823","affiliations":[{"raw_affiliation_string":"School of Computer Science, and Engineering, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.9519,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80745405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"1730","last_page":"1734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9358000159263611,"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":0.9358000159263611,"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/T10863","display_name":"Voice and Speech Disorders","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.005900000222027302,"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/cluster-analysis","display_name":"Cluster analysis","score":0.5507000088691711},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5126000046730042},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4999000132083893},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49230000376701355},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4745999872684479},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46790000796318054},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4537000060081482},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4357999861240387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141999840736389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7311999797821045},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5396000146865845},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46790000796318054},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4587000012397766},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4357999861240387},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.36059999465942383},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.26579999923706055},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2020.3025410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3025410","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2004.13595","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.13595","pdf_url":"https://arxiv.org/pdf/2004.13595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2004.13595","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.13595","pdf_url":"https://arxiv.org/pdf/2004.13595","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2514741789","https://openalex.org/W2559260703","https://openalex.org/W2587088898","https://openalex.org/W2603567530","https://openalex.org/W2752796333","https://openalex.org/W2767052532","https://openalex.org/W2903739847","https://openalex.org/W2907262790","https://openalex.org/W2940544976","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972817752","https://openalex.org/W3005962597","https://openalex.org/W3015922793","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6730333270","https://openalex.org/W6757632829","https://openalex.org/W6768219873","https://openalex.org/W6778247133"],"related_works":[],"abstract_inverted_index":{"Attention-based":[0],"sequence-to-sequence":[1],"(seq2seq)":[2],"speech":[3,37,46,56,113,139,154],"synthesis":[4,38],"has":[5],"achieved":[6],"extraordinary":[7],"performance.":[8],"But":[9],"a":[10,68,94,137],"studio-quality":[11],"corpus":[12],"with":[13,63,78,126,155],"manual":[14],"transcription":[15],"is":[16],"necessary":[17],"to":[18,30,73,92,158],"train":[19],"such":[20],"seq2seq":[21,35],"systems.":[22],"In":[23],"this":[24],"letter,":[25],"we":[26,66,90],"propose":[27,67,91],"an":[28,111],"approach":[29,123,134],"build":[31],"high-quality":[32,153],"and":[33,52,104,128,152],"stable":[34],"based":[36,70,135],"system":[39,143,160],"using":[40],"challenging":[41],"found":[42,147],"data,":[43],"where":[44],"training":[45,103],"contains":[47],"noisy":[48,146],"interferences":[49],"(acoustic":[50],"noise)":[51],"texts":[53],"are":[54],"imperfect":[55],"recognition":[57],"transcripts":[58],"(textual":[59],"noise).":[60],"To":[61],"deal":[62],"text-side":[64,127],"noise,":[65,89],"VQVAE":[69],"heuristic":[71],"method":[72],"compensate":[74],"erroneous":[75],"linguistic":[76],"feature":[77,96],"phonetic":[79],"information":[80],"learned":[81],"directly":[82],"from":[83],"speech.":[84],"As":[85],"for":[86],"the":[87,98,118,121,132,159,163],"speech-side":[88,129],"learn":[93],"noise-independent":[95],"in":[97,124],"auto-regressive":[99],"decoder":[100],"through":[101],"adversarial":[102],"data":[105,148],"augmentation,":[106],"which":[107],"does":[108],"not":[109],"need":[110],"extra":[112],"enhancement":[114,140],"model.":[115],"Experiments":[116],"show":[117],"effectiveness":[119],"of":[120],"proposed":[122],"dealing":[125],"noise.":[130],"Surpassing":[131],"denoising":[133],"on":[136,145,162],"state-of-the-art":[138],"model,":[141],"our":[142],"built":[144,161],"can":[149],"synthesize":[150],"clean":[151,164],"MOS":[156],"close":[157],"counterpart.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2020-05-13T00:00:00"}