{"id":"https://openalex.org/W4225303561","doi":"https://doi.org/10.1109/icassp43922.2022.9746744","title":"Prosodyspeech: Towards Advanced Prosody Model for Neural Text-to-Speech","display_name":"Prosodyspeech: Towards Advanced Prosody Model for Neural Text-to-Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225303561","doi":"https://doi.org/10.1109/icassp43922.2022.9746744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746744","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5113099688","display_name":"Yuanhao Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuanhao Yi","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103063104","display_name":"Shifeng Pan","orcid":"https://orcid.org/0000-0002-9338-7800"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shifeng Pan","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063120829","display_name":"Yujia Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yujia Xiao","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7582","last_page":"7586"},"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":0.9991000294685364,"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":0.9990000128746033,"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":0.9633811712265015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.747934103012085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6597689390182495},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.522204577922821},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5027730464935303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4839187264442444},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.45363694429397583},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45229068398475647},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42760491371154785},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10632380843162537}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9633811712265015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747934103012085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6597689390182495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.522204577922821},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5027730464935303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4839187264442444},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.45363694429397583},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45229068398475647},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42760491371154785},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10632380843162537},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746744","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1576227399","https://openalex.org/W1990505856","https://openalex.org/W2156146072","https://openalex.org/W2165143604","https://openalex.org/W2766812927","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2803832867","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2921059071","https://openalex.org/W2946200149","https://openalex.org/W2948238043","https://openalex.org/W2963609956","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2973046048","https://openalex.org/W3015212100","https://openalex.org/W3015645837","https://openalex.org/W3016021263","https://openalex.org/W3033411150","https://openalex.org/W3095199334","https://openalex.org/W3128910262","https://openalex.org/W3168542456","https://openalex.org/W4232613155","https://openalex.org/W4289383906","https://openalex.org/W4295521014","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6735913928","https://openalex.org/W6739901393","https://openalex.org/W6745697700","https://openalex.org/W6750489868","https://openalex.org/W6752051073","https://openalex.org/W6753855596","https://openalex.org/W6755300632","https://openalex.org/W6763316926","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6780226713","https://openalex.org/W6790220310"],"related_works":["https://openalex.org/W2579204149","https://openalex.org/W2395605663","https://openalex.org/W3081565196","https://openalex.org/W2331826121","https://openalex.org/W1980719954","https://openalex.org/W321531528","https://openalex.org/W3196438084","https://openalex.org/W2181773877","https://openalex.org/W1866214668","https://openalex.org/W2154878481"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"ProsodySpeech,":[3],"a":[4,30,35,44,72,77],"novel":[5],"prosody":[6,47,82,95],"model":[7,137],"to":[8,14,42,64,75,112],"enhance":[9],"encoder-decoder":[10],"neural":[11],"Text-To-Speech":[12],"(TTS),":[13],"generate":[15,43],"high":[16],"expressive":[17,124],"and":[18,128,151],"personalized":[19,130],"speech":[20,37],"even":[21],"with":[22,39,86,107,144],"very":[23],"limited":[24],"training":[25],"data.":[26],"First,":[27],"we":[28,70],"use":[29,71],"Prosody":[31,73],"Extractor":[32],"built":[33],"from":[34,49],"large":[36],"corpus":[38],"various":[40],"speakers":[41],"set":[45],"of":[46,80,89,103,149],"exemplars":[48,83],"multiple":[50],"reference":[51],"speeches,":[52],"in":[53,84,147],"which":[54],"Mutual":[55],"Information":[56],"based":[57],"Style":[58],"content":[59],"separation":[60],"(MIST)":[61],"is":[62,97],"adopted":[63],"alleviate":[65],"\"content":[66],"leakage\"":[67],"problem.":[68],"Second,":[69],"Distributor":[74],"make":[76],"soft":[78],"selection":[79],"appropriate":[81],"phone-level":[85,109],"the":[87,101,114,135],"help":[88],"an":[90],"attention":[91],"mechanism.":[92],"The":[93,132],"resulting":[94],"feature":[96,111],"then":[98],"aggregated":[99],"into":[100,120],"output":[102],"text":[104],"encoder,":[105],"together":[106],"additional":[108],"pitch":[110],"enrich":[113],"prosody.":[115],"We":[116],"apply":[117],"this":[118],"method":[119],"two":[121],"tasks:":[122],"highly":[123],"multi":[125],"style/emotion":[126],"TTS":[127],"few-shot":[129],"TTS.":[131],"experiments":[133],"show":[134],"proposed":[136],"outperforms":[138],"baseline":[139],"FastSpeech":[140],"2":[141],"+":[142],"GST":[143],"significant":[145],"improvements":[146],"terms":[148],"similarity":[150],"style":[152],"expression.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}