{"id":"https://openalex.org/W4392930183","doi":"https://doi.org/10.1109/lsp.2024.3377588","title":"Variable-Length Speaker Conditioning in Flow-Based Text-to-Speech","display_name":"Variable-Length Speaker Conditioning in Flow-Based Text-to-Speech","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392930183","doi":"https://doi.org/10.1109/lsp.2024.3377588"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3377588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3377588","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/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":true,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-1319-8215","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"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, Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4689-3110","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"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":"Minchan Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8150-765X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"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, Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, 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/I4210164379"],"apc_list":null,"apc_paid":null,"fwci":0.9934,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78388062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"899","last_page":"903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9837999939918518,"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":0.9837999939918518,"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":0.9567000269889832,"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/T12031","display_name":"Speech and dialogue systems","score":0.946399986743927,"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/speech-recognition","display_name":"Speech recognition","score":0.747240424156189},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6735690236091614},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.49463745951652527},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4566163420677185},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.4333394765853882},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41070619225502014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33352571725845337},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18350014090538025},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14750897884368896}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.747240424156189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735690236091614},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.49463745951652527},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4566163420677185},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.4333394765853882},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41070619225502014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33352571725845337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18350014090538025},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14750897884368896},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3377588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3377588","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2942623420","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3016159759","https://openalex.org/W3095199334","https://openalex.org/W3096831136","https://openalex.org/W3097777922","https://openalex.org/W3167533889","https://openalex.org/W3213544594","https://openalex.org/W4307783813","https://openalex.org/W4312095868","https://openalex.org/W4313148337","https://openalex.org/W4319587015","https://openalex.org/W4377079685","https://openalex.org/W4379924545","https://openalex.org/W4384615685","https://openalex.org/W4385822697","https://openalex.org/W6640963894","https://openalex.org/W6750489868","https://openalex.org/W6772349387","https://openalex.org/W6790220310","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6846600677","https://openalex.org/W6847363464","https://openalex.org/W6852870047","https://openalex.org/W6854199242"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2640905660"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3],"propose":[4],"a":[5,12,38,57,82],"novel":[6],"speaker":[7,78,87,103],"conditioning":[8],"technique":[9],"that":[10],"leverages":[11],"variable-length":[13,53],"reference":[14,46],"embedding":[15,54],"sequence":[16,55],"for":[17,56],"flow-based":[18,71],"text-to-speech":[19,28],"(TTS)":[20],"architecture":[21,73],"in":[22,70,100],"the":[23,44,65,86,92,95,112],"context":[24],"of":[25,85,94,102],"zero-shot":[26],"multi-speaker":[27],"(ZSM-TTS).":[29],"Unlike":[30],"conventional":[31],"ZSM-TTS":[32],"methods,":[33],"which":[34],"usually":[35],"rely":[36],"on":[37],"single":[39],"fixed-dimensional":[40],"vector":[41],"to":[42,51,111],"represent":[43],"entire":[45],"speech,":[47],"our":[48],"approach":[49],"aims":[50],"extract":[52],"more":[58],"flexible":[59],"and":[60,107],"efficient":[61],"conditioning.":[62,79,88],"We":[63],"enhance":[64],"current":[66],"affine":[67],"coupling":[68],"function":[69],"TTS":[72],"by":[74],"introducing":[75],"an":[76],"attentive":[77],"This":[80],"allows":[81],"local":[83],"variation":[84],"Our":[89],"experiments":[90],"demonstrate":[91],"effectiveness":[93],"proposed":[96],"method,":[97],"highlighting":[98],"improvements":[99],"terms":[101],"similarity,":[104],"speech":[105,108],"naturalness,":[106],"intelligibility":[109],"compared":[110],"baseline":[113],"methods.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}