{"id":"https://openalex.org/W4392904093","doi":"https://doi.org/10.1109/icassp48485.2024.10445828","title":"Spontts: Modeling and Transferring Spontaneous Style for TTS","display_name":"Spontts: Modeling and Transferring Spontaneous Style for TTS","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904093","doi":"https://doi.org/10.1109/icassp48485.2024.10445828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445828","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/A5016567570","display_name":"Hanzhao Li","orcid":"https://orcid.org/0009-0005-3215-7517"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanzhao Li","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113065048","display_name":"L. Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,China","School of Data Science, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047221","display_name":"Yang Song","orcid":"https://orcid.org/0000-0002-1759-1340"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Song","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104124393","display_name":"Yunlin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlin Chen","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co. Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co. Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016567570"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":3.1559,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.922565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12171","last_page":"12175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/naturalness","display_name":"Naturalness","score":0.7871069312095642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5908850431442261},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.48811396956443787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4610878825187683},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4344474673271179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37661486864089966},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09072837233543396}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7871069312095642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5908850431442261},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.48811396956443787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4610878825187683},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4344474673271179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37661486864089966},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09072837233543396},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445828","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":[{"score":0.6000000238418579,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1992245461","https://openalex.org/W2519091744","https://openalex.org/W2726515241","https://openalex.org/W2747070883","https://openalex.org/W2748900206","https://openalex.org/W2884144203","https://openalex.org/W2962788625","https://openalex.org/W2973177710","https://openalex.org/W3016151952","https://openalex.org/W3024869864","https://openalex.org/W3151309757","https://openalex.org/W3162508345","https://openalex.org/W3174758275","https://openalex.org/W3193700177","https://openalex.org/W3197478142","https://openalex.org/W3198152857","https://openalex.org/W3203407300","https://openalex.org/W4297841509","https://openalex.org/W4372260509","https://openalex.org/W4385823196","https://openalex.org/W6640963894","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6798096123","https://openalex.org/W6800795324"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W169399214"],"abstract_inverted_index":{"Spontaneous":[0],"speaking":[1,8],"style":[2,81,128,156,175,179,197],"exhibits":[3],"notable":[4],"differences":[5],"from":[6,99,130],"other":[7],"styles":[9],"due":[10],"to":[11,37,76,95,123,152,162,180],"various":[12],"spontaneous":[13,42,49,52,58,80,97,106,112,127,139,155,174,185,196,210],"phenomena":[14,107,113,140],"(e.g.,":[15,23],"filled":[16],"pauses,":[17],"prolongation)":[18],"and":[19,26,39,78,103,137,176,191,204],"substantial":[20],"prosody":[21,98,136],"variation":[22],"diverse":[24],"pitch":[25],"duration":[27],"variation,":[28],"occasional":[29],"non-verbal":[30],"speech":[31,53,186,211],"like":[32],"a":[33,67,90,100,120,125,149],"smile),":[34],"posing":[35],"challenges":[36],"modeling":[38,173],"prediction":[40,115],"of":[41,47,111,206],"style.":[43],"Moreover,":[44],"the":[45,85,105,109,131,135,144,154,159,163,178,181,202],"limitation":[46],"high-quality":[48],"data":[50],"constrains":[51],"generation":[54],"for":[55,82,212],"speakers":[56],"without":[57],"data.":[59],"To":[60],"address":[61],"these":[62],"problems,":[63],"we":[64,88,118,147],"propose":[65],"SponTTS,":[66],"two-stage":[68],"approach":[69],"based":[70],"on":[71],"neural":[72],"bottleneck":[73],"(BN)":[74],"features":[75],"model":[77],"transfer":[79,153],"TTS.":[83],"In":[84,143],"first":[86,160],"stage,":[87,146],"adopt":[89,148],"Conditional":[91],"Variational":[92],"Autoencoder":[93],"(CVAE)":[94],"capture":[96],"BN":[101],"feature":[102],"involve":[104],"by":[108],"constraint":[110],"embedding":[114],"loss.":[116],"Besides,":[117],"introduce":[119],"flow-based":[121],"predictor":[122],"predict":[124],"latent":[126],"representation":[129],"text,":[132],"which":[133],"enriches":[134],"context-specific":[138],"during":[141],"inference.":[142],"second":[145],"VITS-like":[150],"module":[151],"learned":[157],"in":[158,172,208],"stage":[161],"target":[164,182],"speakers.":[165,214],"Experiments":[166],"demonstrate":[167],"that":[168],"SponTTS":[169,207],"is":[170],"effective":[171],"transferring":[177],"speakers,":[183],"generating":[184,209],"with":[187],"high":[188],"naturalness,":[189],"expressiveness,":[190],"speaker":[192],"similarity.":[193],"The":[194],"zero-shot":[195],"TTS":[198],"test":[199],"further":[200],"verifies":[201],"generalization":[203],"robustness":[205],"unseen":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}