{"id":"https://openalex.org/W4372266971","doi":"https://doi.org/10.1109/icassp49357.2023.10095866","title":"Context-Aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook Speech Synthesis","display_name":"Context-Aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook Speech Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266971","doi":"https://doi.org/10.1109/icassp49357.2023.10095866"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5087759001","display_name":"Shun Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"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"],"is_corresponding":true,"raw_author_name":"Shun Lei","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089348821","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0000-0003-4984-2252"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","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/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyang Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","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/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"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"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen","The Chinese University of Hong Kong, Hong Kong SAR","Peng Cheng Lab, Shenzhen","Shenzhen International Graduate School, Tsinghua University, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Peng Cheng Lab, Shenzhen","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"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"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["XVerse Inc.,Shenzhen","XVerse Inc., Shenzhen"],"affiliations":[{"raw_affiliation_string":"XVerse Inc.,Shenzhen","institution_ids":["https://openalex.org/I4210152717"]},{"raw_affiliation_string":"XVerse Inc., Shenzhen","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":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR","The Chinese University of Hong Kong, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087759001"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8728,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77858023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.994700014591217,"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":0.7486716508865356},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7471202611923218},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7459613680839539},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7398130893707275},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6015807390213013},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5975739359855652},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5953131318092346},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5620478391647339},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5616555213928223},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5011148452758789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4755553603172302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486716508865356},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7471202611923218},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7459613680839539},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7398130893707275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6015807390213013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5975739359855652},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5953131318092346},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5620478391647339},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5616555213928223},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5011148452758789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4755553603172302},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"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":24,"referenced_works":["https://openalex.org/W2000633092","https://openalex.org/W2484713420","https://openalex.org/W2807717950","https://openalex.org/W2885800352","https://openalex.org/W2945260553","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2970597249","https://openalex.org/W3092028330","https://openalex.org/W3158374895","https://openalex.org/W3163339651","https://openalex.org/W3174758275","https://openalex.org/W3196027980","https://openalex.org/W4221159457","https://openalex.org/W4221165968","https://openalex.org/W4295036296","https://openalex.org/W4296068797","https://openalex.org/W4297841650","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6762122294","https://openalex.org/W6763701032","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W258725851","https://openalex.org/W1998701884","https://openalex.org/W3016124757","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3034520363","https://openalex.org/W3149582125","https://openalex.org/W4281476908","https://openalex.org/W157238252","https://openalex.org/W2169632867"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,30],"text-to-speech":[3],"have":[4],"significantly":[5],"improved":[6],"the":[7,50,54],"expressiveness":[8],"of":[9,53,80],"synthesized":[10],"speech.":[11],"However,":[12],"it":[13],"is":[14,68],"still":[15],"challenging":[16],"to":[17],"generate":[18,88,114],"speech":[19,46,90,115],"with":[20,63,91,116],"contextually":[21],"appropriate":[22],"and":[23,75,94,100,119,128],"coherent":[24,39,92,120],"speaking":[25,40,121],"style":[26,41,51,61,78,93,122],"for":[27,44,125],"multi-sentence":[28,129],"text":[29],"audiobooks.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,86],"propose":[36],"a":[37,57,64,104],"context-aware":[38,60],"prediction":[42],"method":[43],"audiobook":[45,106],"synthesis.":[47],"To":[48],"predict":[49],"embedding":[52],"current":[55],"utterance,":[56],"hierarchical":[58],"transformer-based":[59],"predictor":[62],"mixture":[65],"attention":[66],"mask":[67],"designed,":[69],"considering":[70],"both":[71,126],"text-side":[72],"context":[73],"information":[74,79],"speech-":[76],"side":[77],"previous":[81],"speeches.":[82],"Based":[83],"on":[84,103],"this,":[85],"can":[87,113],"long-form":[89],"prosody":[95],"sentence":[96],"by":[97],"sentence.":[98],"Objective":[99],"subjective":[101],"evaluations":[102],"Mandarin":[105],"dataset":[107],"demonstrate":[108],"that":[109],"our":[110],"proposed":[111],"model":[112],"more":[117],"expressive":[118],"than":[123],"baselines,":[124],"single-sentence":[127],"test":[130],"<sup":[131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[133],".":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}