{"id":"https://openalex.org/W4375869201","doi":"https://doi.org/10.1109/icassp49357.2023.10096530","title":"Prosody-Aware Speecht5 for Expressive Neural TTS","display_name":"Prosody-Aware Speecht5 for Expressive Neural TTS","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869201","doi":"https://doi.org/10.1109/icassp49357.2023.10096530"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096530","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096530","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":"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/A5079798556","display_name":"Yan Deng","orcid":"https://orcid.org/0000-0002-0778-6144"},"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":"Yan Deng","raw_affiliation_strings":["Microsoft,China","Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"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":"Long Zhou","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113099688","display_name":"Yuanhao Yi","orcid":null},"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":"Yuanhao Yi","raw_affiliation_strings":["Microsoft,China","Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"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":"Shujie Liu","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","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,China","Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":1.0,"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":1.0,"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":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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/prosody","display_name":"Prosody","score":0.8642597198486328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7547667026519775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5771313905715942},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5377801656723022},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5191485285758972},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5137542486190796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4897015392780304},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45449793338775635},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43862244486808777},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06992647051811218},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06382974982261658}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8642597198486328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547667026519775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5771313905715942},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5377801656723022},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5191485285758972},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5137542486190796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4897015392780304},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45449793338775635},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43862244486808777},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06992647051811218},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06382974982261658},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096530","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096530","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2903739847","https://openalex.org/W2907916773","https://openalex.org/W2963609956","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2973217961","https://openalex.org/W2995181338","https://openalex.org/W3016137096","https://openalex.org/W3097777922","https://openalex.org/W3161296985","https://openalex.org/W3162948689","https://openalex.org/W3163339651","https://openalex.org/W3197324626","https://openalex.org/W3198048667","https://openalex.org/W3205644108","https://openalex.org/W4221159457","https://openalex.org/W4252337780","https://openalex.org/W4280561221","https://openalex.org/W4296068816","https://openalex.org/W4395957972","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6757699683","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6803425590","https://openalex.org/W6838721020"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"SpeechT5,":[0],"a":[1,23,38],"multimodal":[2],"learning":[3],"framework":[4],"which":[5,50],"explores":[6],"encoder-decoder":[7],"pre-training":[8],"by":[9,36,142],"leveraging":[10],"both":[11],"unlabeled":[12,80],"speech":[13,27,81,139],"and":[14,82,88,125],"text,":[15],"has":[16],"been":[17],"proven":[18],"to":[19,56],"be":[20,76],"effective":[21,100],"on":[22,41],"wide":[24],"variety":[25],"of":[26,105],"processing":[28],"tasks.":[29],"In":[30,64],"this":[31],"paper,":[32],"we":[33],"enhance":[34],"SpeechT5":[35,67,98],"adding":[37],"new":[39],"sub-task":[40],"prosody":[42,134],"modeling":[43],"(prosody-aware":[44],"SpeechT5)":[45],"for":[46,120,127],"neural":[47,73,106],"text-to-speech":[48],"(TTS),":[49],"can":[51,75],"improve":[52],"the":[53,65,95,103,111,133],"model":[54],"capability":[55],"learn":[57],"richer":[58],"contextual":[59],"representations":[60],"through":[61],"multi-task":[62],"learning.":[63],"prosody-aware":[66,97],"training":[68],"framework,":[69],"most":[70],"modules":[71],"in":[72,137,144],"TTS":[74],"pre-trained":[77],"with":[78],"large-scale":[79],"text":[83],"corpus,":[84],"including":[85],"encoder,":[86],"decoder,":[87],"variance":[89],"adaptor.":[90],"Experimental":[91],"results":[92],"show":[93],"that":[94],"proposed":[96],"is":[99,118],"at":[101],"improving":[102],"expressiveness":[104],"TTS<sup":[107],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[108],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>:":[109],"1)":[110],"CMOS":[112],"(comparison":[113],"mean":[114],"opinion":[115],"score)":[116],"gain":[117],"0.154":[119],"texts":[121,128],"from":[122,129],"news":[123],"domain":[124],"0.114":[126],"audiobook":[130],"domain;":[131],"2)":[132],"related":[135],"issues":[136],"synthetic":[138],"are":[140],"reduced":[141],"19.02%":[143],"subjective":[145],"evaluation.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}