{"id":"https://openalex.org/W4392902644","doi":"https://doi.org/10.1109/icassp48485.2024.10446098","title":"Latent Filling: Latent Space Data Augmentation for Zero-Shot Speech Synthesis","display_name":"Latent Filling: Latent Space Data Augmentation for Zero-Shot Speech Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902644","doi":"https://doi.org/10.1109/icassp48485.2024.10446098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5060429696","display_name":"Jae\u2010sung Bae","orcid":"https://orcid.org/0000-0002-8270-0072"},"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":true,"raw_author_name":"Jae-Sung Bae","raw_affiliation_strings":["Samsung Research,Seoul,Republic of Korea","Samsung Research, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"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,Seoul,Republic of Korea","Samsung Research, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413487","display_name":"Jihyun Lee","orcid":"https://orcid.org/0000-0001-7051-2587"},"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":"Ji-Hyun Lee","raw_affiliation_strings":["Samsung Research,Seoul,Republic of Korea","Samsung Research, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","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":"Seongkyu Mun","raw_affiliation_strings":["Samsung Research,Seoul,Republic of Korea","Samsung Research, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113699509","display_name":"Taehwa Kang","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":"Taehwa Kang","raw_affiliation_strings":["Samsung Research,Seoul,Republic of Korea","Samsung Research, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"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":"Hoon-Young Cho","raw_affiliation_strings":["Samsung Research,Seoul,Republic of Korea","Samsung Research, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Korea University,Seoul,Republic of Korea","Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5060429696"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":1.0878,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79287918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11166","last_page":"11170"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.9962000250816345,"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":0.7113529443740845},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6489579677581787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.642772376537323},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5574547648429871},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5515642762184143},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5483216047286987},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5280089378356934},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4725639224052429},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44765836000442505},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4210098385810852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35826271772384644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113529443740845},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6489579677581787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.642772376537323},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5574547648429871},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5515642762184143},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5483216047286987},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5280089378356934},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4725639224052429},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44765836000442505},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4210098385810852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35826271772384644},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2030582787","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W2998572311","https://openalex.org/W3024869864","https://openalex.org/W3095389792","https://openalex.org/W3161492781","https://openalex.org/W3196001064","https://openalex.org/W3196584150","https://openalex.org/W3197186969","https://openalex.org/W3213029956","https://openalex.org/W4221166168","https://openalex.org/W4224301045","https://openalex.org/W4225320802","https://openalex.org/W4225746985","https://openalex.org/W4283777098","https://openalex.org/W4293363567","https://openalex.org/W4296068781","https://openalex.org/W4298357738","https://openalex.org/W4313148337","https://openalex.org/W4313679638","https://openalex.org/W4385823117","https://openalex.org/W4390075359","https://openalex.org/W6735249503","https://openalex.org/W6745136726","https://openalex.org/W6755135894","https://openalex.org/W6772349387","https://openalex.org/W6778823374","https://openalex.org/W6788979403","https://openalex.org/W6790220310","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6853888607","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"Previous":[0],"works":[1],"in":[2,35,67],"zero-shot":[3],"text-to-speech":[4],"(ZS-TTS)":[5],"have":[6],"attempted":[7],"to":[8,32],"enhance":[9],"its":[10],"systems":[11,89],"by":[12],"enlarging":[13],"the":[14,25,36,48,68,73,91],"training":[15,95],"data":[16,29,65],"through":[17],"crowd-sourcing":[18],"or":[19],"augmenting":[20,47],"existing":[21,87],"speech":[22,108],"data.":[23],"However,":[24],"use":[26],"of":[27,45,72],"low-quality":[28],"has":[30],"led":[31],"a":[33,53,78],"decline":[34],"overall":[37],"system":[38],"performance.":[39],"To":[40],"avoid":[41],"such":[42],"degradation,":[43],"instead":[44],"directly":[46],"input":[49],"data,":[50],"we":[51],"propose":[52],"latent":[54,63],"filling":[55],"(LF)":[56],"method":[57],"that":[58,100],"adopts":[59],"simple":[60],"but":[61],"effective":[62],"space":[64,71],"augmentation":[66],"speaker":[69,104],"embedding":[70],"ZS-TTS":[74,88],"system.":[75],"By":[76],"incorporating":[77],"consistency":[79],"loss,":[80],"LF":[81,101],"can":[82],"be":[83],"seamlessly":[84],"integrated":[85],"into":[86],"without":[90],"need":[92],"for":[93],"additional":[94],"stages.":[96],"Experimental":[97],"results":[98],"show":[99],"significantly":[102],"improves":[103],"similarity":[105],"while":[106],"preserving":[107],"quality.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}