{"id":"https://openalex.org/W4283836776","doi":"https://doi.org/10.21437/interspeech.2022-570","title":"Learning Noise-independent Speech Representation for High-quality Voice Conversion for Noisy Target Speakers","display_name":"Learning Noise-independent Speech Representation for High-quality Voice Conversion for Noisy Target Speakers","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283836776","doi":"https://doi.org/10.21437/interspeech.2022-570"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-570","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"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":"Liumeng Xue","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100557412","display_name":"Shan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685461","display_name":"Na Hu","orcid":"https://orcid.org/0000-0001-6362-0969"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Hu","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066245750","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-9051-2111"},"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":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2076,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39438113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2548","last_page":"2552"},"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":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.7569747567176819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7512456178665161},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5899897813796997},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5274448990821838},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5226594805717468},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4869316816329956},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4171852171421051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3237702250480652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569747567176819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7512456178665161},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5899897813796997},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5274448990821838},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5226594805717468},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4869316816329956},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4171852171421051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3237702250480652},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-570","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2022125261","https://openalex.org/W2025768430","https://openalex.org/W2036428220","https://openalex.org/W2187089797","https://openalex.org/W2518172956","https://openalex.org/W2531207078","https://openalex.org/W2559260703","https://openalex.org/W2576309025","https://openalex.org/W2577350056","https://openalex.org/W2760103357","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2963539064","https://openalex.org/W2964069186","https://openalex.org/W2964243274","https://openalex.org/W2972597685","https://openalex.org/W2996286887","https://openalex.org/W2997069303","https://openalex.org/W3015338123","https://openalex.org/W3025192522","https://openalex.org/W3026874504","https://openalex.org/W3092028330","https://openalex.org/W3096864844","https://openalex.org/W3128442956","https://openalex.org/W3163568691","https://openalex.org/W3194805633","https://openalex.org/W3198869563","https://openalex.org/W3207065451","https://openalex.org/W3213305849","https://openalex.org/W4226075807","https://openalex.org/W4231961043","https://openalex.org/W4285757699","https://openalex.org/W4288079962","https://openalex.org/W4288337064","https://openalex.org/W4289761690","https://openalex.org/W4306291601","https://openalex.org/W4372142139"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Building":[0],"a":[1,20,52,68,109,133,147],"voice":[2,60,178],"conversion":[3,36,61,82,142,179],"system":[4],"for":[5,58,62,140,180],"noisy":[6,13,63,181],"target":[7,64,77,182],"speakers,":[8],"such":[9],"as":[10],"users":[11],"providing":[12],"samples":[14],"or":[15],"Internet":[16],"found":[17],"data,":[18],"is":[19,84],"challenging":[21],"task":[22],"since":[23],"the":[24,35,42,76,81,87,91,101,115,122,129,138,141,152,166,177],"use":[25,146],"of":[26,44,90,154],"contaminated":[27],"speech":[28,54,171],"in":[29,128,137,176],"model":[30,83,149,168],"training":[31],"will":[32],"apparently":[33],"degrade":[34],"performance.In":[37],"this":[38,94],"paper,":[39],"we":[40,66,73,96,107,145],"leverage":[41],"advances":[43],"our":[45],"recently":[46],"proposed":[47,167],"Glow-WaveGAN":[48],"[1]":[49],"and":[50,124,173],"propose":[51],"noise-independent":[53,116],"representation":[55,118],"learning":[56],"approach":[57],"high-quality":[59],"speakers.Specifically,":[65],"learn":[67,151],"latent":[69,102,158],"feature":[70,103],"space":[71,131],"where":[72],"ensure":[74],"that":[75,165],"distribution":[78,89,153],"modeled":[79,88],"by":[80,121],"exactly":[85],"from":[86,119,160],"waveform":[92,120],"generator.With":[93],"premise,":[95],"further":[97],"manage":[98],"to":[99,104,150],"make":[100],"be":[105],"noise-invariant.Specifically,":[106],"introduce":[108],"noise-controllable":[110],"WaveGAN,":[111],"which":[112],"directly":[113],"learns":[114],"acoustic":[117],"encoder":[123],"conducts":[125],"noise":[126],"control":[127],"hidden":[130],"through":[132],"FiLM":[134],"[2]":[135],"module":[136],"decoder.As":[139],"model,":[143],"importantly,":[144],"flow-based":[148],"noiseindependent":[155],"but":[156],"speaker-related":[157],"features":[159],"phoneme":[161],"posteriorgrams.Experimental":[162],"results":[163],"demonstrate":[164],"achieves":[169],"high":[170],"quality":[172],"speaker":[174],"similarity":[175],"speakers.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}