{"id":"https://openalex.org/W4313148337","doi":"https://doi.org/10.1109/lsp.2022.3226655","title":"SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech","display_name":"SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4313148337","doi":"https://doi.org/10.1109/lsp.2022.3226655"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3226655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3226655","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":["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/A5101424423","display_name":"Byoung Jin Choi","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"]},{"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":true,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","Samsung Research, Samsung Electronics"],"raw_orcid":"https://orcid.org/0000-0003-1319-8215","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Samsung Research, Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103069095","display_name":"Myeonghun Jeong","orcid":"https://orcid.org/0000-0002-4689-3110"},"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"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","De-partment of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul 08826, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4689-3110","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"De-partment of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul 08826, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018167","display_name":"Joun Yeop Lee","orcid":"https://orcid.org/0000-0002-3316-4808"},"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":"Joun Yeop Lee","raw_affiliation_strings":["Samsung Research, Samsung Electronics Co., Ltd, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics Co., Ltd, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"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"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","De-partment of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul 08826, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"De-partment of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul 08826, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101424423"],"corresponding_institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":1.1098,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82028204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"2502","last_page":"2506"},"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9955000281333923,"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":0.6904284358024597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6793158054351807},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6335468888282776},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5710121989250183},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5223221182823181},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5205658078193665},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.46303021907806396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34626859426498413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32135432958602905},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20339566469192505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904284358024597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6793158054351807},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6335468888282776},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5710121989250183},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5223221182823181},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5205658078193665},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.46303021907806396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34626859426498413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32135432958602905},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20339566469192505},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3226655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3226655","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W129217914","https://openalex.org/W1583912456","https://openalex.org/W1600722501","https://openalex.org/W1861150963","https://openalex.org/W1924770834","https://openalex.org/W1935012542","https://openalex.org/W1959608418","https://openalex.org/W2081976287","https://openalex.org/W2096555739","https://openalex.org/W2144139079","https://openalex.org/W2502312327","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2603777577","https://openalex.org/W2767052532","https://openalex.org/W2788357188","https://openalex.org/W2794490148","https://openalex.org/W2808706139","https://openalex.org/W2903739847","https://openalex.org/W2942623420","https://openalex.org/W2946200149","https://openalex.org/W2947196194","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3015826515","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3090254849","https://openalex.org/W3128910262","https://openalex.org/W3167533889","https://openalex.org/W3168527213","https://openalex.org/W3169905056","https://openalex.org/W3174285493","https://openalex.org/W3196584150","https://openalex.org/W3198575134","https://openalex.org/W4225680573","https://openalex.org/W4287761884","https://openalex.org/W4288337064","https://openalex.org/W4289761690","https://openalex.org/W4297798428","https://openalex.org/W4312095868","https://openalex.org/W6605232188","https://openalex.org/W6635084905","https://openalex.org/W6640212811","https://openalex.org/W6640963894","https://openalex.org/W6714644935","https://openalex.org/W6724804524","https://openalex.org/W6748588790","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6752910514","https://openalex.org/W6763832098","https://openalex.org/W6772349387","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6783527727","https://openalex.org/W6790220310","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6846492496"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Zero-shot":[0],"multi-speaker":[1,44],"text-to-speech":[2,45],"(ZSM-TTS)":[3],"models":[4,47],"aim":[5],"to":[6,25,49,66],"generate":[7],"a":[8,85,99,103,121,134,158],"speech":[9,96,152],"sample":[10],"with":[11],"the":[12,27,36,51,55,61,67,78,114,117,145,151],"voice":[13],"characteristic":[14],"of":[15,22,35,60,131,150],"an":[16,128],"unseen":[17,32,94],"speaker.":[18],"The":[19,107,140],"main":[20],"challenge":[21],"ZSM-TTS":[23,159],"is":[24,48],"increase":[26],"overall":[28],"speaker":[29,39,69,80,95,122,136,155],"similarity":[30,156],"for":[31,42,93,133],"speakers.":[33],"One":[34],"most":[37],"successful":[38],"conditioning":[40,81,105,142],"methods":[41],"flow-based":[43],"(TTS)":[46],"utilize":[50],"functions":[52],"which":[53,91],"predict":[54],"scale":[56],"and":[57,154],"bias":[58],"parameters":[59,118],"affine":[62,87],"coupling":[63,88,110],"layers":[64],"according":[65],"given":[68],"embedding":[70,123,137],"vector.":[71],"In":[72],"this":[73],"letter,":[74],"we":[75],"improve":[76],"on":[77],"previous":[79],"method":[82],"by":[83,116],"introducing":[84],"speaker-normalized":[86],"(SNAC)":[89],"layer":[90,111],"allows":[92],"synthesis":[97],"in":[98,148,157],"zero-shot":[100],"manner":[101],"leveraging":[102],"normalization-based":[104],"technique.":[106],"newly":[108],"designed":[109],"explicitly":[112],"normalizes":[113],"input":[115],"predicted":[119],"from":[120],"vector":[124],"while":[125],"training,":[126],"enabling":[127],"inverse":[129],"process":[130],"denormalizing":[132],"new":[135],"at":[138],"inference.":[139],"proposed":[141],"scheme":[143],"yields":[144],"state-of-the-art":[146],"performance":[147],"terms":[149],"quality":[153],"setting.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}