{"id":"https://openalex.org/W4221156079","doi":"https://doi.org/10.1109/icassp43922.2022.9746875","title":"nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-Shot Multi-speaker text-to-speech","display_name":"nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-Shot Multi-speaker text-to-speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221156079","doi":"https://doi.org/10.1109/icassp43922.2022.9746875"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746875","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101811604","display_name":"Botao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botao Zhao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210164150"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028437800","display_name":"Xulong Zhang","orcid":"https://orcid.org/0000-0001-7005-992X"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xulong Zhang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4293","last_page":"4297"},"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":0.9988999962806702,"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":0.996999979019165,"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/autoencoder","display_name":"Autoencoder","score":0.8168072700500488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204833030700684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6904775500297546},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6477577686309814},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5601856708526611},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5534399747848511},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5489412546157837},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5078502297401428},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4779803156852722},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45821091532707214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4447915554046631},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4390440285205841},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4122334122657776},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1697131097316742},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15803343057632446},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07202094793319702}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8168072700500488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204833030700684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6904775500297546},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6477577686309814},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5601856708526611},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5534399747848511},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5489412546157837},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5078502297401428},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4779803156852722},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45821091532707214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447915554046631},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4390440285205841},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4122334122657776},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1697131097316742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15803343057632446},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07202094793319702},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/icassp43922.2022.9746875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746875","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1499798934","https://openalex.org/W2188365844","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2946200149","https://openalex.org/W2962717182","https://openalex.org/W2963609956","https://openalex.org/W2972359262","https://openalex.org/W2972574864","https://openalex.org/W2972659941","https://openalex.org/W2973084242","https://openalex.org/W3015826515","https://openalex.org/W3016159759","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3097531247","https://openalex.org/W3097728852","https://openalex.org/W3128910262","https://openalex.org/W3168527213","https://openalex.org/W4210729123","https://openalex.org/W6629687487","https://openalex.org/W6687045409","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6761768988","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6785090365","https://openalex.org/W6790220310","https://openalex.org/W6795807602","https://openalex.org/W6807955952","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Multi-speaker":[0],"text-to-speech":[1],"(TTS)":[2],"using":[3,35,42],"a":[4,9,19,28,43,58,66],"few":[5],"adaption":[6,38,115],"data":[7],"is":[8,82],"challenge":[10],"in":[11],"practical":[12],"applications.":[13],"To":[14],"address":[15],"that,":[16],"we":[17],"propose":[18],"zero-shot":[20],"multi-speaker":[21],"TTS,":[22],"named":[23],"nnSpeech,":[24],"that":[25,103],"could":[26,106],"synthesis":[27],"new":[29,52],"speaker":[30,44,72],"voice":[31],"without":[32],"fine-tuning":[33],"and":[34,63,74,91,100,109],"only":[36,113],"one":[37,114],"utterance.":[39],"Compared":[40],"with":[41,112],"representation":[45],"module":[46],"to":[47],"extract":[48],"the":[49,95],"characteristics":[50,73],"of":[51],"speakers,":[53],"our":[54,104],"method":[55],"bases":[56],"on":[57,88,94],"speaker-guided":[59],"conditional":[60],"variational":[61],"autoencoder":[62],"can":[64],"generate":[65,107],"variable":[67,79,86],"Z,":[68],"which":[69],"contains":[70],"both":[71],"content":[75],"information.":[76],"The":[77],"latent":[78],"Z":[80],"distribution":[81],"approximated":[83],"by":[84],"another":[85],"conditioned":[87],"reference":[89],"mel-spectrogram":[90],"phoneme.":[92],"Experiments":[93],"English":[96],"corpus,":[97,99],"Mandarin":[98],"cross-dataset":[101],"proves":[102],"model":[105],"natural":[108],"similar":[110],"speech":[111],"speech.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":11}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}