{"id":"https://openalex.org/W4392903361","doi":"https://doi.org/10.1109/icassp48485.2024.10446352","title":"Stylespeech: Self-Supervised Style Enhancing with VQ-VAE-Based Pre-Training for Expressive Audiobook Speech Synthesis","display_name":"Stylespeech: Self-Supervised Style Enhancing with VQ-VAE-Based Pre-Training for Expressive Audiobook Speech Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903361","doi":"https://doi.org/10.1109/icassp48485.2024.10446352"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446352","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":"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/A5108049724","display_name":"Xueyuan Chen","orcid":"https://orcid.org/0000-0003-0493-839X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xueyuan Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442237","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0002-0434-7939"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Microsoft,Beijing,China","Microsoft, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084317268","display_name":"Shaofei Zhang","orcid":"https://orcid.org/0000-0002-8377-2270"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Zhang","raw_affiliation_strings":["Microsoft,Beijing,China","Microsoft, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft,Beijing,China","Microsoft, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8448,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91922754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12316","last_page":"12320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9945999979972839,"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":0.750607967376709},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7403987646102905},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6355118751525879},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.616443932056427},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5892212986946106},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46194109320640564},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.45765814185142517},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4323924779891968},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4263845682144165},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4251297116279602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41288521885871887},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35246336460113525},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.265511155128479},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08836326003074646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750607967376709},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7403987646102905},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6355118751525879},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.616443932056427},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5892212986946106},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46194109320640564},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.45765814185142517},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4323924779891968},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4263845682144165},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4251297116279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41288521885871887},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35246336460113525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.265511155128479},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08836326003074646},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446352","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":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2407139314","https://openalex.org/W2752796333","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W3035323028","https://openalex.org/W3092028330","https://openalex.org/W3094917204","https://openalex.org/W3160584619","https://openalex.org/W3163339651","https://openalex.org/W3171153522","https://openalex.org/W4224928640","https://openalex.org/W4225326644","https://openalex.org/W4226230180","https://openalex.org/W4283689139","https://openalex.org/W4319586244","https://openalex.org/W4365799947","https://openalex.org/W4391156274","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6751878434","https://openalex.org/W6774314701","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"The":[0],"expressive":[1,40],"quality":[2],"of":[3,55,75,106,127],"synthesized":[4,129],"speech":[5,42,130],"for":[6,39,135],"audiobooks":[7],"is":[8,49,67,91],"limited":[9],"by":[10],"generalized":[11],"model":[12,95],"architecture":[13,86],"and":[14,98,112,125,138],"unbalanced":[15],"style":[16,33,47,62,81,100,108],"distribution":[17],"in":[18,26,69,131],"the":[19,96,104,107,123,128,136],"training":[20],"data.":[21,58],"To":[22],"address":[23],"these":[24],"issues,":[25],"this":[27],"paper,":[28],"we":[29],"propose":[30],"a":[31,45,52,60,70,84],"self-supervised":[32,71],"enhancing":[34],"method":[35,119],"with":[36,51,73,87,103],"VQ-VAE-based":[37],"pre-training":[38],"audiobook":[41,132],"synthesis.":[43],"Firstly,":[44],"text":[46],"encoder":[48],"pre-trained":[50,68],"large":[53],"amount":[54],"unlabeled":[56],"text-only":[57],"Secondly,":[59],"spectrogram":[61],"extractor":[63],"based":[64],"on":[65],"VQ-VAE":[66],"manner,":[72],"plenty":[74],"audio":[76],"data":[77],"that":[78,116],"covers":[79],"complex":[80],"variations.":[82],"Then":[83],"novel":[85],"two":[88],"encoder-decoder":[89],"paths":[90],"specially":[92],"designed":[93],"to":[94],"pronunciation":[97],"high-level":[99],"expressiveness":[101,126],"respectively,":[102],"guidance":[105],"extractor.":[109],"Both":[110],"objective":[111],"subjective":[113],"evaluations":[114],"demonstrate":[115],"our":[117],"proposed":[118],"can":[120],"effectively":[121],"improve":[122],"naturalness":[124],"synthesis":[133],"especially":[134],"role":[137],"out-of-domain":[139],"scenarios.1":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}