{"id":"https://openalex.org/W4385486424","doi":"https://doi.org/10.1109/taslp.2023.3301217","title":"MSStyleTTS: Multi-Scale Style Modeling With Hierarchical Context Information for Expressive Speech Synthesis","display_name":"MSStyleTTS: Multi-Scale Style Modeling With Hierarchical Context Information for Expressive Speech Synthesis","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385486424","doi":"https://doi.org/10.1109/taslp.2023.3301217"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3301217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3301217","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/A5103014224","display_name":"Shun Lei","orcid":"https://orcid.org/0000-0003-3597-3913"},"institutions":[{"id":"https://openalex.org/I4210152717","display_name":"Mavenir (Israel)","ror":"https://ror.org/0507wc250","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210152717"]},{"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","IL"],"is_corresponding":false,"raw_author_name":"Shun Lei","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Xverse Inc"],"raw_orcid":"https://orcid.org/0000-0003-3597-3913","affiliations":[{"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"]},{"raw_affiliation_string":"Xverse Inc","institution_ids":["https://openalex.org/I4210152717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749226","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0009-0002-6363-891X"},"institutions":[{"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":"Yixuan Zhou","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-6363-891X","affiliations":[{"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/A5101849127","display_name":"Liyang Chen","orcid":"https://orcid.org/0000-0001-6985-8281"},"institutions":[{"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":"Liyang Chen","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6985-8281","affiliations":[{"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/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"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":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-0524","affiliations":[{"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":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-9543-1572","affiliations":[{"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":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Skywork AI Pte. Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8304-5260","affiliations":[{"raw_affiliation_string":"Skywork AI Pte. Ltd., Beijing, China","institution_ids":[]}]},{"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"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"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"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0548,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80846962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3290","last_page":"3303"},"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7632100582122803},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7254038453102112},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.7193202972412109},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6958655118942261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6536912322044373},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5787662863731384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47758129239082336},{"id":"https://openalex.org/keywords/style-analysis","display_name":"Style analysis","score":0.4769655466079712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4302595555782318},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4114886522293091},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0793774425983429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632100582122803},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7254038453102112},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7193202972412109},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6958655118942261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6536912322044373},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5787662863731384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47758129239082336},{"id":"https://openalex.org/C2776172590","wikidata":"https://www.wikidata.org/wiki/Q7629421","display_name":"Style analysis","level":4,"score":0.4769655466079712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4302595555782318},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4114886522293091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0793774425983429},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"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/C189188589","wikidata":"https://www.wikidata.org/wiki/Q14864997","display_name":"Investment management","level":3,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3301217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3301217","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W38285298","https://openalex.org/W1522301498","https://openalex.org/W1584787447","https://openalex.org/W1599623585","https://openalex.org/W1600722501","https://openalex.org/W1861172732","https://openalex.org/W1924770834","https://openalex.org/W2102003408","https://openalex.org/W2110332474","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2141340689","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2470673105","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2952127920","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2967220154","https://openalex.org/W2970597249","https://openalex.org/W2973158936","https://openalex.org/W2973217961","https://openalex.org/W3007067948","https://openalex.org/W3010916717","https://openalex.org/W3016137096","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3092028330","https://openalex.org/W3097538987","https://openalex.org/W3113076898","https://openalex.org/W3146550708","https://openalex.org/W3150572638","https://openalex.org/W3152136404","https://openalex.org/W3158374895","https://openalex.org/W3163339651","https://openalex.org/W3174758275","https://openalex.org/W3195592874","https://openalex.org/W3196027980","https://openalex.org/W3197216873","https://openalex.org/W3197704090","https://openalex.org/W4210777104","https://openalex.org/W4221159457","https://openalex.org/W4221165968","https://openalex.org/W4225303561","https://openalex.org/W4226230180","https://openalex.org/W4280604450","https://openalex.org/W4283689139","https://openalex.org/W4289383906","https://openalex.org/W4295036296","https://openalex.org/W4295731579","https://openalex.org/W4297841650","https://openalex.org/W4385245566","https://openalex.org/W4391602018","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6640963894","https://openalex.org/W6739901393","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6755300632","https://openalex.org/W6756197946","https://openalex.org/W6763701032","https://openalex.org/W6764498146","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W2369835347","https://openalex.org/W2366288806","https://openalex.org/W2923994139","https://openalex.org/W3092341862","https://openalex.org/W2380844718","https://openalex.org/W4403997720","https://openalex.org/W2078494085","https://openalex.org/W2973194270","https://openalex.org/W2388524959","https://openalex.org/W2366737344"],"abstract_inverted_index":{"Expressive":[0],"speech":[1,49,76,150],"synthesis":[2],"is":[3,118],"crucial":[4],"for":[5,74],"many":[6],"human-computer":[7],"interaction":[8],"scenarios,":[9],"such":[10],"as":[11],"audiobooks,":[12],"podcasts,":[13],"and":[14,42,61,80,102,132,139,151,161,185],"voice":[15],"assistants.":[16],"Previous":[17],"works":[18],"focus":[19],"on":[20,158],"predicting":[21],"the":[22,30,33,122,148,154,167,172,179,182],"style":[23,46,71,100,104,134,145,155,187],"embeddings":[24,135],"at":[25,83,136],"one":[26],"single":[27],"scale":[28],"from":[29,86,147],"information":[31,38,125,184],"within":[32],"current":[34],"sentence.":[35,95],"Whereas,":[36],"context":[37,91,124,131,183],"in":[39,47,130],"neighboring":[40],"sentences":[41],"multi-scale":[43,99,103,144,186],"nature":[44],"of":[45,90,181],"human":[48],"are":[50,106],"neglected,":[51],"making":[52],"it":[53],"challenging":[54],"to":[55,78,120],"convert":[56],"multi-sentence":[57],"text":[58],"into":[59],"natural":[60],"expressive":[62,75],"speech.":[63],"In":[64,175],"this":[65],"paper,":[66],"we":[67,177],"propose":[68],"MSStyleTTS,":[69],"a":[70,87,94,110],"modeling":[72],"method":[73,169],"synthesis,":[77],"capture":[79],"predict":[81,133],"styles":[82],"different":[84],"levels":[85],"wider":[88],"range":[89],"rather":[92],"than":[93],"Two":[96],"sub-modules,":[97],"including":[98],"extractor":[101,142],"predictor,":[105],"trained":[107],"together":[108],"with":[109],"FastSpeech":[111],"2":[112],"based":[113],"acoustic":[114],"model.":[115],"The":[116,141],"predictor":[117],"designed":[119],"explore":[121],"hierarchical":[123],"by":[126],"considering":[127],"structural":[128],"relationships":[129],"global-level,":[137],"sentence-level":[138],"subword-level.":[140],"extracts":[143],"embedding":[146],"ground-truth":[149],"explicitly":[152],"guides":[153],"prediction.":[156],"Evaluations":[157],"both":[159],"in-domain":[160],"out-of-domain":[162],"audiobook":[163],"datasets":[164],"demonstrate":[165],"that":[166,189],"proposed":[168],"significantly":[170],"outperforms":[171],"three":[173],"baselines.":[174],"addition,":[176],"conduct":[178],"analysis":[180],"representations":[188],"have":[190],"never":[191],"been":[192],"discussed":[193],"before.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}