{"id":"https://openalex.org/W3162948689","doi":"https://doi.org/10.1109/icassp39728.2021.9413864","title":"Speech Bert Embedding for Improving Prosody in Neural TTS","display_name":"Speech Bert Embedding for Improving Prosody in Neural TTS","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162948689","doi":"https://doi.org/10.1109/icassp39728.2021.9413864","mag":"3162948689"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100430201","display_name":"Liping Chen","orcid":"https://orcid.org/0009-0003-6453-5645"},"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":"Liping Chen","raw_affiliation_strings":["Microsoft China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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/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":"Xi Wang","raw_affiliation_strings":["Microsoft China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"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":"Frank K. Soong","raw_affiliation_strings":["Microsoft China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft China","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"],"raw_orcid":null,"affiliations":[{"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":1.6118,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86321047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6563","last_page":"6567"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.910088300704956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6948003768920898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6914055943489075},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5771376490592957},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46416524052619934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4025171101093292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40069806575775146}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.910088300704956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948003768920898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6914055943489075},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5771376490592957},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46416524052619934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4025171101093292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40069806575775146}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2619368999","https://openalex.org/W2758785877","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/W2903853691","https://openalex.org/W2904459034","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2963341956","https://openalex.org/W2963609956","https://openalex.org/W2963618559","https://openalex.org/W2963712897","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2965373594","https://openalex.org/W2970730223","https://openalex.org/W2972359262","https://openalex.org/W2981991061","https://openalex.org/W2998572311","https://openalex.org/W3033194228","https://openalex.org/W3036601975","https://openalex.org/W3086459521","https://openalex.org/W3095545636","https://openalex.org/W3099782249","https://openalex.org/W4295731579","https://openalex.org/W6745117592","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6756197946","https://openalex.org/W6757322325","https://openalex.org/W6763832098","https://openalex.org/W6765987481","https://openalex.org/W6766673545","https://openalex.org/W6769238691","https://openalex.org/W6772349387","https://openalex.org/W6780218876","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3203313352","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W152045069","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W2612504417","https://openalex.org/W652196294"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,27,36,66,129],"speech":[4,13,21,40,138],"BERT":[5,103,159,190],"model":[6],"to":[7,83,112,115],"extract":[8,105],"embedded":[9],"prosody":[10,18,33,114,119,160,191],"information":[11],"in":[12,22,69,88,178,198],"segments":[14],"for":[15,163],"improving":[16],"the":[17,48,54,62,70,81,85,89,96,101,117,121,136,148,155,158,175,179,188],"of":[19,39,65,120],"synthesized":[20],"neural":[23],"text-to-speech":[24],"(TTS).":[25],"As":[26],"pre-trained":[28],"model,":[29],"it":[30],"can":[31,43,104],"learn":[32],"attributes":[34],"from":[35,61],"large":[37],"amount":[38],"data,":[41],"which":[42,109],"utilize":[44],"more":[45],"data":[46,51],"than":[47],"original":[49,140],"training":[50],"used":[52,78],"by":[53,95],"target":[55],"TTS.":[56],"The":[57,73,124],"embedding":[58,75,161],"is":[59,76,110,151,184],"extracted":[60,74],"previous":[63],"segment":[64,87],"fixed":[67],"length":[68],"proposed":[71,102,149],"BERT.":[72],"then":[77],"together":[79],"with":[80,187],"mel-spectrogram":[82],"predict":[84],"following":[86],"TTS":[90,98,122,132,156,193],"decoder.":[91],"Experimental":[92],"results":[93],"obtained":[94],"Transformer":[97],"show":[99,146],"that":[100,147],"fine-grained,":[106],"segment-level":[107],"prosody,":[108],"complementary":[111],"utterance-level":[113],"improve":[116],"final":[118],"speech.":[123],"objective":[125],"distortions":[126],"measured":[127],"on":[128],"single":[130],"speaker":[131],"are":[133,197],"reduced":[134],"between":[135],"generated":[137],"and":[139,166,174],"recordings.":[141],"Subjective":[142],"listening":[143],"tests":[144],"also":[145],"approach":[150],"favorably":[152],"preferred":[153],"over":[154],"without":[157],"module,":[162],"both":[164],"in-domain":[165],"out-of-domain":[167],"applications.":[168],"For":[169],"Microsoft":[170],"professional,":[171],"single/multiple":[172],"speakers":[173],"LJ":[176],"Speaker":[177],"public":[180],"database,":[181],"subjective":[182],"preference":[183],"similarly":[185],"confirmed":[186],"new":[189],"embedding.":[192],"demo":[194],"audio":[195],"samples":[196],"https://judy44chen.github.io/TTSSpeechBERT/.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}