{"id":"https://openalex.org/W4283640572","doi":"https://doi.org/10.21437/interspeech.2022-46","title":"SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech","display_name":"SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283640572","doi":"https://doi.org/10.21437/interspeech.2022-46"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-46","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.12132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041144868","display_name":"Hyunjae Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunjae Cho","raw_affiliation_strings":["MINDsLab Inc., Republic of Korea","Seoul National University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc., Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083897431","display_name":"Wonbin Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonbin Jung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea","MINDsLab Inc., Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"MINDsLab Inc., Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072915273","display_name":"Junhyeok Lee","orcid":"https://orcid.org/0000-0002-4950-5371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhyeok Lee","raw_affiliation_strings":["MINDsLab Inc., Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc., Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066846974","display_name":"Sang Hoon Woo","orcid":"https://orcid.org/0000-0002-8805-3443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sang Hoon Woo","raw_affiliation_strings":["MINDsLab Inc., Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc., Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8563520908355713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6943172216415405},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5762024521827698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5728030204772949},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4965971112251282},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39280417561531067},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3740893006324768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33682316541671753},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.12362077832221985},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07877957820892334}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8563520908355713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6943172216415405},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5762024521827698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5728030204772949},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4965971112251282},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39280417561531067},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3740893006324768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33682316541671753},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.12362077832221985},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07877957820892334},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-46","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"},{"id":"pmh:oai:arXiv.org:2206.12132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12132","pdf_url":"https://arxiv.org/pdf/2206.12132","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:2206.12132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12132","pdf_url":"https://arxiv.org/pdf/2206.12132","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2120847449","https://openalex.org/W2133564696","https://openalex.org/W2766812927","https://openalex.org/W2808706139","https://openalex.org/W2936832667","https://openalex.org/W2946200149","https://openalex.org/W2963090522","https://openalex.org/W2963609956","https://openalex.org/W2963925437","https://openalex.org/W2964243274","https://openalex.org/W2969049672","https://openalex.org/W2972359262","https://openalex.org/W2972473628","https://openalex.org/W2973084242","https://openalex.org/W2990124956","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3094002217","https://openalex.org/W3095012670","https://openalex.org/W3150572638","https://openalex.org/W3168527213","https://openalex.org/W3197294703","https://openalex.org/W4225276642","https://openalex.org/W4225680573","https://openalex.org/W4287111656","https://openalex.org/W4287121924","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3008587939","https://openalex.org/W4400488565","https://openalex.org/W4296070390"],"abstract_inverted_index":{"In":[0,94],"this":[1,78],"paper,":[2],"we":[3],"present":[4],"SANE-TTS,":[5],"a":[6],"stable":[7],"and":[8,106],"natural":[9],"end-to-end":[10],"multilingual":[11,19,25,56],"TTS":[12,26,57],"model.":[13],"By":[14],"the":[15,110],"difficulty":[16],"of":[17,88,124],"obtaining":[18],"corpus":[20],"for":[21],"given":[22],"speaker,":[23],"training":[24],"model":[27,81],"with":[28,68,84],"monolingual":[29],"corpora":[30],"is":[31,52,114],"unavoidable.":[32],"We":[33],"introduce":[34],"speaker":[35,62,66,90,119],"regularization":[36,63],"loss":[37],"that":[38,123],"improves":[39],"speech":[40],"naturalness":[41,99],"during":[42],"cross-lingual":[43,75,92,105,129],"synthesis":[44],"as":[45,47],"well":[46],"domain":[48],"adversarial":[49],"training,":[50],"which":[51],"applied":[53],"in":[54,71,91,104,128],"other":[55],"models.":[58],"Furthermore,":[59],"by":[60],"adding":[61],"loss,":[64],"replacing":[65],"embedding":[67],"zero":[69],"vector":[70],"duration":[72],"predictor":[73],"stabilizes":[74],"inference.":[76,130],"With":[77],"replacement,":[79],"our":[80,136],"generates":[82],"speeches":[83],"moderate":[85],"rhythm":[86],"regardless":[87],"source":[89],"synthesis.":[93],"MOS":[95],"evaluation,":[96],"SANE-TTS":[97,117],"achieves":[98],"score":[100,113],"above":[101],"3.80":[102],"both":[103],"intralingual":[107],"synthesis,":[108],"where":[109],"ground":[111,125],"truth":[112,126],"3.99.":[115],"Also,":[116],"maintains":[118],"similarity":[120],"close":[121],"to":[122],"even":[127],"Audio":[131],"samples":[132],"are":[133],"available":[134],"on":[135],"web":[137],"page.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2022-06-29T00:00:00"}