{"id":"https://openalex.org/W4377079685","doi":"https://doi.org/10.1109/lsp.2023.3277786","title":"SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems","display_name":"SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377079685","doi":"https://doi.org/10.1109/lsp.2023.3277786"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3277786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3277786","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/A5085480169","display_name":"Hyungchan Yoon","orcid":"https://orcid.org/0000-0002-6331-2437"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]},{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyungchan Yoon","raw_affiliation_strings":["Clova Voice, Naver Corp, Seongnam, South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Clova Voice, Naver Corp, Seongnam, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645547","display_name":"Changhwan Kim","orcid":"https://orcid.org/0000-0002-7718-4958"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changhwan Kim","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074612173","display_name":"Seyun Um","orcid":"https://orcid.org/0000-0002-2229-6741"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seyun Um","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032657615","display_name":"Hyun-Wook Yoon","orcid":"https://orcid.org/0000-0002-2849-4140"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-Wook Yoon","raw_affiliation_strings":["Clova Voice, Naver Corp, Seongnam, South Korea","Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Clova Voice, Naver Corp, Seongnam, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085480169"],"corresponding_institution_ids":["https://openalex.org/I193775966","https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":1.5711,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8600672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"593","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9972000122070312,"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":0.7769700288772583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7347818613052368},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6699135303497314},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.660553514957428},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5909152030944824},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5868787169456482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47402551770210266},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.410591721534729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32443687319755554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7769700288772583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7347818613052368},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6699135303497314},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.660553514957428},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5909152030944824},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5868787169456482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47402551770210266},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.410591721534729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32443687319755554},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3277786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3277786","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":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2284050935","https://openalex.org/W2519091744","https://openalex.org/W2531409750","https://openalex.org/W2619368999","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2808706139","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3015645837","https://openalex.org/W3016159759","https://openalex.org/W3024869864","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3095199334","https://openalex.org/W3095545636","https://openalex.org/W3097777922","https://openalex.org/W3128910262","https://openalex.org/W3161704465","https://openalex.org/W3167533889","https://openalex.org/W3168527213","https://openalex.org/W3169905056","https://openalex.org/W4221166168","https://openalex.org/W4225680573","https://openalex.org/W4225746985","https://openalex.org/W4280542470","https://openalex.org/W4295731579","https://openalex.org/W4297798428","https://openalex.org/W4313148337","https://openalex.org/W4385245566","https://openalex.org/W6695676441","https://openalex.org/W6714644935","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6763832098","https://openalex.org/W6765987481","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6790220310","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6839013216"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2096510939","https://openalex.org/W2161543916"],"abstract_inverted_index":{"This":[0],"letter":[1],"proposes":[2],"an":[3],"effective":[4],"speaker-conditioning":[5],"method":[6],"that":[7,119],"is":[8],"applicable":[9],"to":[10,69,107],"zero-shot":[11],"multi-speaker":[12],"text-to-speech":[13],"(ZSM-TTS)":[14],"systems.":[15],"Based":[16],"on":[17],"the":[18,22,36,40,52,73,78,85,91,120,125],"inductive":[19,80],"bias":[20,81],"in":[21,26,31,95,129],"speech":[23,88],"generation":[24],"task,":[25],"which":[27],"local":[28,93],"context":[29,94],"information":[30],"text/phoneme":[32],"sequences":[33,71],"heavily":[34],"affect":[35],"speaker":[37,63,113],"characteristics":[38],"of":[39,87,131],"output":[41],"speech,":[42],"we":[43],"propose":[44],"a":[45],"Speaker-Conditional":[46],"Convolutional":[47],"Neural":[48],"Network":[49],"(SC-CNN)":[50],"for":[51],"ZSM-TTS":[53,105,127],"task.":[54],"SC-CNN":[55,123],"first":[56],"predicts":[57],"convolutional":[58],"kernels":[59],"from":[60],"each":[61],"learned":[62],"embedding,":[64],"then":[65],"applies":[66],"1-D":[67],"convolutions":[68],"phoneme":[70],"with":[72,122],"predicted":[74],"kernels.":[75],"It":[76],"utilizes":[77],"aforementioned":[79],"and":[82,103,134],"effectively":[83],"models":[84,121,128],"characteristic":[86],"by":[89],"providing":[90],"speaker-specific":[92],"phonetic":[96],"domain.":[97],"We":[98],"also":[99],"build":[100],"both":[101,132],"FastSpeech2":[102],"VITS-based":[104],"systems":[106],"verify":[108],"its":[109],"superiority":[110],"over":[111],"conventional":[112],"conditioning":[114],"methods.":[115],"The":[116],"results":[117],"confirm":[118],"outperform":[124],"recent":[126],"terms":[130],"subjective":[133],"objective":[135],"measurements.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}