{"id":"https://openalex.org/W4412353446","doi":"https://doi.org/10.1109/tnnls.2025.3584944","title":"HierSpeech++: Bridging the Gap Between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-Shot Speech Synthesis","display_name":"HierSpeech++: Bridging the Gap Between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-Shot Speech Synthesis","publication_year":2025,"publication_date":"2025-07-11","ids":{"openalex":"https://openalex.org/W4412353446","doi":"https://doi.org/10.1109/tnnls.2025.3584944","pmid":"https://pubmed.ncbi.nlm.nih.gov/40644087"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3584944","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3584944","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tnnls.2025.3584944","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033958396","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0000-0002-8925-4474"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]},{"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":true,"raw_author_name":"Sang-Hoon Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102753650","display_name":"Ha-Yeong Choi","orcid":"https://orcid.org/0000-0003-2390-7628"},"institutions":[{"id":"https://openalex.org/I4210149944","display_name":"Korea Telecom (South Korea)","ror":null,"country_code":"KR","type":null,"lineage":["https://openalex.org/I4210149944"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Yeong Choi","raw_affiliation_strings":["Gen AI Lab, KT Corporation, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Gen AI Lab, KT Corporation, Seoul, South Korea","institution_ids":["https://openalex.org/I4210149944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007493723","display_name":"Seung-Bin Kim","orcid":"https://orcid.org/0000-0002-2287-9111"},"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":"Seung-Bin Kim","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2010Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]},{"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":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033958396"],"corresponding_institution_ids":["https://openalex.org/I197347611","https://openalex.org/I57664883"],"apc_list":null,"apc_paid":null,"fwci":20.0195,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99144854,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"36","issue":"10","first_page":"18422","last_page":"18436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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":0.9922999739646912,"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":0.9388999938964844,"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/bridging","display_name":"Bridging (networking)","score":0.8944013118743896},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6848698854446411},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5688155889511108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5521416664123535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48796433210372925},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4739556312561035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39003786444664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3482818305492401},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2950862646102905},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.074625164270401},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.06555303931236267}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8944013118743896},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6848698854446411},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5688155889511108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5521416664123535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48796433210372925},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4739556312561035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39003786444664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3482818305492401},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2950862646102905},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.074625164270401},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.06555303931236267},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3584944","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3584944","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40644087","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40644087","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tnnls.2025.3584944","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3584944","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2115098197","https://openalex.org/W2808631503","https://openalex.org/W2903739847","https://openalex.org/W2963609956","https://openalex.org/W2964138190","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W3013020904","https://openalex.org/W3014225712","https://openalex.org/W3113687514","https://openalex.org/W3163505255","https://openalex.org/W3174285493","https://openalex.org/W3196468212","https://openalex.org/W3213029956","https://openalex.org/W3215615641","https://openalex.org/W4200635083","https://openalex.org/W4221166168","https://openalex.org/W4224920322","https://openalex.org/W4225320802","https://openalex.org/W4225892118","https://openalex.org/W4225956675","https://openalex.org/W4226132755","https://openalex.org/W4252812408","https://openalex.org/W4283215837","https://openalex.org/W4297841714","https://openalex.org/W4372259784","https://openalex.org/W4375869257","https://openalex.org/W4375869358","https://openalex.org/W4385822372","https://openalex.org/W4385823130","https://openalex.org/W4385823135","https://openalex.org/W4385823264","https://openalex.org/W4386133927","https://openalex.org/W4387968164","https://openalex.org/W4389318028","https://openalex.org/W4390075359","https://openalex.org/W4390872297","https://openalex.org/W4393156644","https://openalex.org/W4398152753","https://openalex.org/W4402111456","https://openalex.org/W4402115993","https://openalex.org/W4403791830","https://openalex.org/W4406461672","https://openalex.org/W4406752483"],"related_works":["https://openalex.org/W4408719353","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2043010663"],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)-based":[3],"speech":[4,12,28,47,60,85,89,104,120,134,157,175],"synthesis":[5,61,90],"has":[6],"been":[7],"widely":[8],"adopted":[9],"in":[10,87],"zero-shot":[11,46,88,156,174],"synthesis.":[13,176],"However,":[14],"they":[15],"require":[16],"a":[17,42,102,132,154],"large-scale":[18],"data":[19],"and":[20,34,44,52,68,80,106,114,126,164,179],"possess":[21],"the":[22,66,71,78,96,122,148,170],"same":[23],"limitations":[24],"as":[25],"previous":[26],"autoregressive":[27],"models,":[29],"including":[30],"slow":[31],"inference":[32],"speed":[33],"lack":[35],"of":[36,70,83],"robustness.":[37],"This":[38],"article":[39],"proposes":[40],"HierSpeech++,":[41],"fast":[43],"strong":[45,155],"synthesizer":[48,158],"for":[49],"text-to-speech":[50],"(TTS)":[51],"voice":[53,127],"conversion":[54],"(VC).":[55],"We":[56,129],"verified":[57],"that":[58,147,160],"hierarchical":[59,149],"frameworks":[62],"could":[63,152],"significantly":[64,76],"improve":[65,77],"robustness":[67],"expressiveness":[69],"synthetic":[72,84],"speech.":[73],"Furthermore,":[74],"we":[75,94,168],"naturalness":[79],"speaker":[81],"similarity":[82],"even":[86],"scenarios.":[91],"For":[92],"TTS,":[93],"adopt":[95],"text-to-vec":[97],"(TTV)":[98],"framework,":[99],"which":[100],"generates":[101,119],"self-supervised":[103],"representation":[105,109],"an":[107],"F0":[108],"based":[110],"on":[111],"text":[112],"representations":[113],"prosody":[115],"prompts.":[116],"Then,":[117],"HierSpeech++":[118],"from":[121,138],"generated":[123],"vector,":[124],"F0,":[125],"prompt.":[128],"further":[130],"introduce":[131],"high-efficient":[133],"super-resolution":[135],"(SpeechSR)":[136],"framework":[137],"16":[139],"to":[140],"48":[141],"kHz.":[142],"The":[143],"experimental":[144],"results":[145],"demonstrated":[146],"variational":[150],"autoencoder":[151],"be":[153],"given":[159],"it":[161],"outperforms":[162],"LLM-based":[163],"diffusion-based":[165],"models.":[166],"Moreover,":[167],"achieved":[169],"first":[171],"human-level":[172],"quality":[173],"Audio":[177],"samples":[178],"source":[180],"code":[181],"are":[182],"available":[183],"at":[184],"https://github.com/hierspeechpp/code.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}