{"id":"https://openalex.org/W4372341043","doi":"https://doi.org/10.1109/icassp49357.2023.10096247","title":"Improving Speech Prosody of Audiobook Text-To-Speech Synthesis with Acoustic and Textual Contexts","display_name":"Improving Speech Prosody of Audiobook Text-To-Speech Synthesis with Acoustic and Textual Contexts","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341043","doi":"https://doi.org/10.1109/icassp49357.2023.10096247"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096247","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/A5072398606","display_name":"Detai Xin","orcid":"https://orcid.org/0009-0007-1908-1137"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Detai Xin","raw_affiliation_strings":["Rakuten Group, Inc,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan","Rakuten Group, Inc, Japan"],"affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc,Japan","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Rakuten Group, Inc, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054490307","display_name":"Sharath Adavanne","orcid":"https://orcid.org/0000-0002-5001-6911"},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sharath Adavanne","raw_affiliation_strings":["Rakuten Group, Inc,Japan","Rakuten Group, Inc, Japan"],"affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc,Japan","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Rakuten Group, Inc, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027645456","display_name":"Federico Ang","orcid":null},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Federico Ang","raw_affiliation_strings":["Rakuten Group, Inc,Japan","Rakuten Group, Inc, Japan"],"affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc,Japan","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Rakuten Group, Inc, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083494376","display_name":"Ashish Kulkarni","orcid":"https://orcid.org/0000-0002-5713-2202"},"institutions":[{"id":"https://openalex.org/I1301041018","display_name":"Rakuten (Japan)","ror":"https://ror.org/0098kke80","country_code":"JP","type":"company","lineage":["https://openalex.org/I1301041018"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ashish Kulkarni","raw_affiliation_strings":["Rakuten Group, Inc,Japan","Rakuten Group, Inc, Japan"],"affiliations":[{"raw_affiliation_string":"Rakuten Group, Inc,Japan","institution_ids":["https://openalex.org/I1301041018"]},{"raw_affiliation_string":"Rakuten Group, Inc, Japan","institution_ids":["https://openalex.org/I1301041018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072398606"],"corresponding_institution_ids":["https://openalex.org/I1301041018","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.9231,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88411386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"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":0.9977999925613403,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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/prosody","display_name":"Prosody","score":0.8891202807426453},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7421892881393433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412747144699097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6450362205505371},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6003432869911194},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5350618958473206},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4995272159576416},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44906678795814514},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4448377192020416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38404640555381775}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8891202807426453},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7421892881393433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412747144699097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450362205505371},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6003432869911194},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5350618958473206},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4995272159576416},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44906678795814514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4448377192020416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38404640555381775},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096247","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":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1502984613","https://openalex.org/W1522301498","https://openalex.org/W1570629387","https://openalex.org/W1924770834","https://openalex.org/W2000633092","https://openalex.org/W2057563799","https://openalex.org/W2471520273","https://openalex.org/W2612434969","https://openalex.org/W2794490148","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2946200149","https://openalex.org/W2963925437","https://openalex.org/W2964243274","https://openalex.org/W3033411150","https://openalex.org/W3113076898","https://openalex.org/W3162746464","https://openalex.org/W3163339651","https://openalex.org/W3195592874","https://openalex.org/W3196027980","https://openalex.org/W3198217962","https://openalex.org/W4224928640","https://openalex.org/W4295036296","https://openalex.org/W4296068776","https://openalex.org/W4296068791","https://openalex.org/W4296068797","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6737575990","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6763832098","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W2587342322","https://openalex.org/W2540115864"],"abstract_inverted_index":{"We":[0,77],"present":[1,104],"a":[2,54,85],"multi-speaker":[3,86],"Japanese":[4,87],"audiobook":[5,88,120],"text-to-speech":[6],"(TTS)":[7],"system":[8],"that":[9,93,122],"leverages":[10],"multimodal":[11],"context":[12,17,21,43,51,56,60,111],"information":[13,61,115],"of":[14,26,110],"preceding":[15],"acoustic":[16,50],"and":[18,53,62,81,116],"bilateral":[19],"textual":[20,55],"to":[22,58,65,73],"improve":[23],"the":[24,42,66,71,94,107,128],"prosody":[25],"synthetic":[27],"speech.":[28],"Previous":[29],"work":[30],"either":[31],"uses":[32,48],"unilateral":[33],"or":[34],"single-modality":[35],"context,":[36],"which":[37,69],"does":[38],"not":[39],"fully":[40],"represent":[41],"information.":[44],"The":[45],"proposed":[46,95],"method":[47,96],"an":[49],"encoder":[52,57],"aggregate":[59],"feeds":[63],"it":[64],"TTS":[67,121],"model,":[68],"enables":[70],"model":[72],"predict":[74],"context-dependent":[75],"prosody.":[76],"conducted":[78],"comprehensive":[79],"objective":[80],"subjective":[82],"evaluations":[83],"on":[84],"dataset.":[89],"Experimental":[90],"results":[91],"demonstrate":[92],"significantly":[97],"outperforms":[98],"two":[99],"previous":[100],"works.":[101],"Additionally,":[102],"we":[103],"insights":[105],"about":[106],"different":[108],"choices":[109],"-":[112,118],"modalities,":[113],"lateral":[114],"length":[117],"for":[119],"have":[123],"never":[124],"been":[125],"discussed":[126],"in":[127],"literature":[129],"before.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
