{"id":"https://openalex.org/W3202191685","doi":"https://doi.org/10.1145/3458380.3458405","title":"Learning Deep and Wide Contextual Representations Using BERT for Statistical Parametric Speech Synthesis","display_name":"Learning Deep and Wide Contextual Representations Using BERT for Statistical Parametric Speech Synthesis","publication_year":2021,"publication_date":"2021-02-26","ids":{"openalex":"https://openalex.org/W3202191685","doi":"https://doi.org/10.1145/3458380.3458405","mag":"3202191685"},"language":"en","primary_location":{"id":"doi:10.1145/3458380.3458405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458380.3458405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Digital Signal Processing","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/A5100430526","display_name":"Yajie Zhang","orcid":"https://orcid.org/0000-0002-9916-080X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ya-Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100430526"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69062514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"150"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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/T10028","display_name":"Topic Modeling","score":0.9933000206947327,"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":0.8389754295349121},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6840134263038635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6438975930213928},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.6095575094223022},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6039083003997803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6004396080970764},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5945960879325867},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5799076557159424},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5389794111251831},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5280838012695312},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5213950276374817},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4696250259876251},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4627331495285034},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4549138844013214},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42295870184898376},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14595261216163635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389754295349121},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6840134263038635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6438975930213928},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6095575094223022},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6039083003997803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004396080970764},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5945960879325867},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5799076557159424},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5389794111251831},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5280838012695312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5213950276374817},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4696250259876251},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4627331495285034},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4549138844013214},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42295870184898376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14595261216163635},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458380.3458405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458380.3458405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Digital Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8663906801","display_name":null,"funder_award_id":"61871358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":11,"referenced_works":["https://openalex.org/W2120847449","https://openalex.org/W2131774270","https://openalex.org/W2560674852","https://openalex.org/W2885800352","https://openalex.org/W2904459034","https://openalex.org/W2963691546","https://openalex.org/W2964243274","https://openalex.org/W2972881244","https://openalex.org/W2973217961","https://openalex.org/W2980708516","https://openalex.org/W3016137096"],"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/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"In":[0],"this":[1,57],"paper,":[2],"we":[3],"propose":[4],"a":[5,22,64,69],"method":[6],"of":[7,46,51,93,124,133],"learning":[8],"deep":[9,48],"and":[10,35,40,53,68,97,128],"wide":[11],"contextual":[12,76],"representations":[13,50,77],"for":[14],"statistical":[15],"parametric":[16],"speech":[17,135],"synthesis":[18],"(SPSS)":[19],"using":[20],"BERT,":[21],"pre-trained":[23,96],"language":[24],"representation":[25],"model.":[26,106,141],"Traditional":[27],"acoustic":[28,125],"models":[29],"in":[30,104],"SPSS":[31],"utilize":[32],"phoneme":[33],"sequences":[34],"prosody":[36],"labels":[37],"as":[38],"input,":[39],"can":[41,120],"not":[42],"make":[43],"full":[44],"use":[45],"the":[47,75,105,110,122,130,138],"linguistic":[49],"current":[52],"surrounding":[54],"sentences.":[55],"Therefore,":[56],"paper":[58],"designs":[59],"two":[60],"context":[61,66,71,118],"encoders,":[62],"i.e.,":[63],"sentence-window":[65],"encoder":[67],"paragraph-level":[70],"encoder,":[72],"to":[73],"integrate":[74],"extracted":[78],"from":[79],"multiple":[80],"sentences":[81],"by":[82],"BERT":[83,94],"into":[84],"Tacotron2":[85,140],"via":[86],"an":[87],"extra":[88],"attention":[89],"module.":[90],"The":[91],"parameters":[92],"are":[95],"then":[98],"fine-tuned":[99],"together":[100],"with":[101,137],"other":[102],"components":[103],"Experimental":[107],"results":[108],"on":[109],"Blizzard":[111],"Challenge":[112],"2019":[113],"dataset":[114],"show":[115],"that":[116],"both":[117],"encoders":[119],"reduce":[121],"errors":[123],"feature":[126],"prediction":[127],"improve":[129],"subjective":[131],"performance":[132],"synthetic":[134],"comparing":[136],"baseline":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}