{"id":"https://openalex.org/W4226050434","doi":"https://doi.org/10.1109/taslp.2022.3169634","title":"Zero-Shot Normalization Driven Multi-Speaker Text to Speech Synthesis","display_name":"Zero-Shot Normalization Driven Multi-Speaker Text to Speech Synthesis","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226050434","doi":"https://doi.org/10.1109/taslp.2022.3169634"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3169634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3169634","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5108049369","display_name":"Neeraj Kumar","orcid":"https://orcid.org/0000-0002-0485-392X"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neeraj Kumar","raw_affiliation_strings":["Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-0485-392X","affiliations":[{"raw_affiliation_string":"Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109064591","display_name":"Ankur Narang","orcid":null},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankur Narang","raw_affiliation_strings":["Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066116024","display_name":"Brejesh Lall","orcid":"https://orcid.org/0000-0003-2677-3071"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Brejesh Lall","raw_affiliation_strings":["Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-2677-3071","affiliations":[{"raw_affiliation_string":"Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.9185,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77939245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"1679","last_page":"1693"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9979000091552734,"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":0.7361608147621155},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.731337308883667},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7161755561828613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6462225914001465},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.58051598072052},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4190846085548401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3985511362552643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361608147621155},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.731337308883667},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7161755561828613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6462225914001465},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.58051598072052},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4190846085548401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3985511362552643},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3169634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3169634","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W603018635","https://openalex.org/W1491884104","https://openalex.org/W1494198834","https://openalex.org/W1574901103","https://openalex.org/W1901616594","https://openalex.org/W2032291279","https://openalex.org/W2049686551","https://openalex.org/W2085955208","https://openalex.org/W2091425152","https://openalex.org/W2107740512","https://openalex.org/W2107860279","https://openalex.org/W2122410182","https://openalex.org/W2151219630","https://openalex.org/W2157590573","https://openalex.org/W2332013542","https://openalex.org/W2475998840","https://openalex.org/W2736900972","https://openalex.org/W2747874407","https://openalex.org/W2764280570","https://openalex.org/W2766812927","https://openalex.org/W2890964092","https://openalex.org/W2892140764","https://openalex.org/W2899663614","https://openalex.org/W2904459034","https://openalex.org/W2955881930","https://openalex.org/W2962788625","https://openalex.org/W2963223306","https://openalex.org/W2963300588","https://openalex.org/W2963371159","https://openalex.org/W2963433607","https://openalex.org/W2963466847","https://openalex.org/W2964243274","https://openalex.org/W2998572311","https://openalex.org/W3013020904","https://openalex.org/W3015440759","https://openalex.org/W3015826515","https://openalex.org/W3016021263","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3095545636","https://openalex.org/W3095883095","https://openalex.org/W3128910262","https://openalex.org/W3161109662","https://openalex.org/W3196584150","https://openalex.org/W3198429080","https://openalex.org/W4205298730","https://openalex.org/W4212863985","https://openalex.org/W4245242383","https://openalex.org/W4248222719","https://openalex.org/W4287761884","https://openalex.org/W4289286706","https://openalex.org/W4289383906","https://openalex.org/W6677106874","https://openalex.org/W6678087030","https://openalex.org/W6679525913","https://openalex.org/W6687566353","https://openalex.org/W6731370813","https://openalex.org/W6734688555","https://openalex.org/W6738277540","https://openalex.org/W6739901393","https://openalex.org/W6741475896","https://openalex.org/W6745697700","https://openalex.org/W6748573829","https://openalex.org/W6748588790","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6754925833","https://openalex.org/W6755300632","https://openalex.org/W6755977528","https://openalex.org/W6758207765","https://openalex.org/W6763085777","https://openalex.org/W6763832098","https://openalex.org/W6765371447","https://openalex.org/W6772349387","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6790220310"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W1984347656","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2611678594"],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1],"systems":[2],"are":[3],"designed":[4],"to":[5,12,67,140,147,231],"synthesize":[6],"natural":[7],"and":[8,16,54,69,87,121,144,167,181,220,227,264,283],"expressive":[9],"speech,":[10],"adapt":[11],"an":[13,22,33,102,142,178,187],"unseen":[14,23,34,188],"voice,":[15],"capture":[17],"the":[18,62,83,95,127,164,206,214,238,254,291],"speaking":[19,36,78],"style":[20,37,60,76,197],"of":[21,32,46,61,77,97,186,209,256,270,272,290],"speaker":[24,168,241,245,287,293],"by":[25,82,94],"converting":[26],"text":[27,180],"into":[28,38,118],"speech.":[29],"The":[30,59],"introduction":[31],"speaker\u2019s":[35],"a":[39,43,98,123,154,182,199,224,244],"TTS":[40],"system":[41],"offers":[42],"wide":[44],"range":[45],"application":[47],"scenarios,":[48],"including":[49],"personal":[50],"assistant,":[51],"news":[52],"broadcast,":[53],"audio":[55],"navigation,":[56],"among":[57],"others.":[58],"speech":[63,158,184,193,234,281],"varies":[64],"from":[65],"person":[66,68,71],"every":[70],"exhibits":[72],"his":[73],"or":[74],"her":[75],"that":[79,110,129,162,195,278],"is":[80,91,101],"determined":[81],"language,":[84],"demography,":[85],"culture":[86],"other":[88],"factors.":[89],"Style":[90],"best":[92],"captured":[93],"prosody":[96,120],"signal.":[99],"It":[100],"ongoing":[103],"research":[104],"area":[105],"with":[106,170,286],"numerous":[107],"real-world":[108],"applications":[109],"produces":[111],"high-quality":[112],"multi-speaker":[113,157,261],"voice":[114],"synthesis":[115,159],"while":[116],"taking":[117],"account":[119],"in":[122,135,194,198,212,223],"zero-shot":[124,156,200],"manner.":[125,201],"Despite":[126],"fact":[128],"several":[130],"efforts":[131],"have":[132],"been":[133],"made":[134],"this":[136,150],"area,":[137],"it":[138],"continues":[139],"be":[141,229],"interesting":[143],"difficult":[145],"topic":[146],"solve.":[148],"In":[149],"paper,":[151],"we":[152,203],"present":[153],"novel":[155],"approach":[160],"(ZSM-SS)":[161],"leverages":[163],"normalization":[165,210],"architecture":[166,259],"encoder":[169,246,294],"non-autoregressive":[171],"multi-head":[172],"attention":[173],"driven":[174],"encoder-decoder":[175],"architecture.":[176,251],"Given":[177],"input":[179],"reference":[183],"sample":[185],"person,":[189],"ZSM-SS":[190],"can":[191,228],"generate":[192,232,237],"person\u2019s":[196],"Additionally,":[202],"demonstrate":[204,253],"how":[205],"affine":[207],"parameters":[208],"help":[211],"capturing":[213],"prosodic":[215],"features":[216],"such":[217],"as":[218],"energy":[219],"fundamental":[221],"frequency":[222],"disentangled":[225],"fashion":[226],"used":[230],"morphed":[233],"output.":[235],"We":[236,252],"256":[239],"dimensional":[240],"embedding":[242,288],"using":[243,268],"based":[247,250],"on":[248,260],"wav2vec2.0":[249],"efficacy":[255],"our":[257],"proposed":[258,273,292],"VCTK":[262],"[1]":[263],"LibriTTS":[265],"[2]":[266],"datasets,":[267],"visualization":[269],"hessian":[271],"model,":[274],"multiple":[275],"quantitative":[276],"metrics":[277],"measure":[279],"generated":[280],"distortion":[282],"MOS,":[284],"along":[285],"analysis":[289],"model.":[295]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}