{"id":"https://openalex.org/W4296069295","doi":"https://doi.org/10.21437/interspeech.2022-10765","title":"Fine-grained Noise Control for Multispeaker Speech Synthesis","display_name":"Fine-grained Noise Control for Multispeaker Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069295","doi":"https://doi.org/10.21437/interspeech.2022-10765"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10765","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10765","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/A5056672858","display_name":"Karolos Nikitaras","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karolos Nikitaras","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022310876","display_name":"Georgios Vamvoukakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Vamvoukakis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052196585","display_name":"Nikolaos Ellinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Ellinas","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087573028","display_name":"Konstantinos Klapsas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Klapsas","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050072052","display_name":"\u039a\u03c9\u03bd\u03c3\u03c4\u03b1\u03bd\u03c4\u03af\u03bd\u03bf\u03c2 \u039c\u03b1\u03c1\u03ba\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Markopoulos","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111393130","display_name":"Spyros Raptis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spyros Raptis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June Sig Sung","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041656238","display_name":"Gunu Jho","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunu Jho","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091595884","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5056672858"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5197,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63418444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"828","last_page":"832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.979200005531311,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8281756639480591},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.756473183631897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7372021675109863},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.656812846660614},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5683655142784119},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5026333332061768},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49860715866088867},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.45901811122894287},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.449907124042511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4244644045829773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40824198722839355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2743721008300781}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8281756639480591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.756473183631897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372021675109863},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.656812846660614},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5683655142784119},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5026333332061768},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49860715866088867},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.45901811122894287},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.449907124042511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4244644045829773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40824198722839355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2743721008300781},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10765","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10765","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":[{"score":0.49000000953674316,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1574170747","https://openalex.org/W1901129140","https://openalex.org/W2519091744","https://openalex.org/W2559260703","https://openalex.org/W2801554275","https://openalex.org/W2808706139","https://openalex.org/W2907262790","https://openalex.org/W2940703732","https://openalex.org/W2962788625","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W3016021263","https://openalex.org/W3025671734","https://openalex.org/W3033411150","https://openalex.org/W3091928890","https://openalex.org/W3094607766","https://openalex.org/W3095389792","https://openalex.org/W3163906773","https://openalex.org/W3198104520","https://openalex.org/W4287121924","https://openalex.org/W4287761884"],"related_works":["https://openalex.org/W4214652783","https://openalex.org/W258725851","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"A":[0],"text-to-speech":[1],"(TTS)":[2],"model":[3,21],"typically":[4],"factorizes":[5],"speech":[6,32,97],"attributes":[7],"such":[8,44],"as":[9,45],"content,":[10,36],"speaker":[11],"and":[12,38,48,55,58,66,103],"prosody":[13,37,59,82],"into":[14],"disentangled":[15],"representations.Recent":[16],"works":[17],"aim":[18],"to":[19,28,71],"additionally":[20,92],"the":[22,30,76,107],"acoustic":[23],"conditions":[24,47],"explicitly,":[25],"in":[26,69,94,116],"order":[27,70],"disentangle":[29],"primary":[31],"factors,":[33,43],"i.e.":[34],"linguistic":[35],"timbre":[39],"from":[40],"any":[41],"residual":[42],"recording":[46],"background":[49],"noise.This":[50],"paper":[51],"proposes":[52],"unsupervised,":[53],"interpretable":[54],"fine-grained":[56,81],"noise":[57,74],"modeling.We":[60],"incorporate":[61],"adversarial":[62],"training,":[63],"representation":[64],"bottleneck":[65],"utterance-to-frame":[67],"modeling":[68,83],"learn":[72],"frame-level":[73],"representations.To":[75],"same":[77],"end,":[78],"we":[79],"perform":[80],"via":[84],"a":[85],"Fully":[86],"Hierarchical":[87],"Variational":[88],"AutoEncoder":[89],"(FVAE)":[90],"which":[91],"results":[93,99],"more":[95],"expressive":[96],"synthesis.Experimental":[98],"support":[100],"our":[101,117],"claims":[102],"ablation":[104],"studies":[105],"verify":[106],"importance":[108],"of":[109],"each":[110],"proposed":[111],"component.Audio":[112],"samples":[113],"are":[114],"available":[115],"demo":[118],"page":[119],"1":[120],".":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}