{"id":"https://openalex.org/W3095401840","doi":"https://doi.org/10.21437/interspeech.2020-2423","title":"Exploiting Deep Sentential Context for Expressive End-to-End Speech Synthesis","display_name":"Exploiting Deep Sentential Context for Expressive End-to-End Speech Synthesis","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095401840","doi":"https://doi.org/10.21437/interspeech.2020-2423","mag":"3095401840"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2423","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5036283087","display_name":"Fengyu Yang","orcid":"https://orcid.org/0009-0005-5410-4707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengyu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016939864","display_name":"Qinghua Wu","orcid":"https://orcid.org/0000-0002-0598-8367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinghua Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362598","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-0921-0122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9479,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81471675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3436","last_page":"3440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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":0.9951000213623047,"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":0.8407126069068909},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6995892524719238},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6847870945930481},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6128193736076355},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.571263313293457},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5558978915214539},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5472216606140137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058410167694092},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5026347637176514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4271215796470642}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407126069068909},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6995892524719238},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6847870945930481},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6128193736076355},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.571263313293457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5558978915214539},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5472216606140137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058410167694092},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5026347637176514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4271215796470642},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2423","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"Attention-based":[0],"seq2seq":[1,51],"text-to-speech":[2],"systems,":[3],"especially":[4],"those":[5],"use":[6],"self-attention":[7],"networks":[8],"(SAN),":[9],"have":[10],"achieved":[11],"state-of-art":[12],"performance.":[13],"But":[14],"an":[15,66,94],"expressive":[16,70,95,171],"corpus":[17,96],"with":[18,182],"rich":[19],"prosody":[20],"is":[21,62,81,190],"still":[22],"challenging":[23],"to":[24,43,65,87,117,123,160],"model":[25],"as":[26],"1)":[27,140],"prosodic":[28,54,185],"aspects,":[29],"which":[30,61,80,143,156],"span":[31],"across":[32],"different":[33,110,149,165],"sentential":[34,91,106],"granularities":[35],"and":[36,45,47,113,152,187],"mainly":[37],"determine":[38],"acoustic":[39],"expressiveness,":[40],"are":[41],"difficult":[42],"quantize":[44],"label":[46],"2)":[48,153],"the":[49,90,125,128,146],"current":[50],"framework":[52],"extracts":[53],"information":[55,108],"solely":[56],"from":[57,109],"a":[58,77,119],"text":[59,85],"encoder,":[60,86],"easily":[63],"collapsed":[64],"averaged":[67],"expression":[68],"for":[69,97,164],"contents.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75,133],"propose":[76],"context":[78,92,101,107,138],"extractor,":[79],"built":[82],"upon":[83],"SAN-based":[84],"sufficiently":[88],"exploit":[89],"over":[93],"seq2seq-based":[98],"TTS.":[99],"Our":[100],"extractor":[102],"first":[103],"collects":[104],"prosodic-related":[105],"SAN":[111,150,166],"layers":[112],"then":[114],"aggregates":[115],"them":[116],"learn":[118,162],"comprehensive":[120],"sentence":[121],"representation":[122],"enhance":[124],"expressiveness":[126],"of":[127,137,148],"final":[129],"generated":[130],"speech.":[131],"Specifically,":[132],"investigate":[134],"two":[135,170],"methods":[136],"aggregation:":[139],"direct":[141],"aggregation":[142,155,189],"directly":[144],"concatenates":[145],"outputs":[147],"layers,":[151],"weighted":[154,188],"uses":[157],"multi-head":[158],"attention":[159],"automatically":[161],"contributions":[163],"layers.":[167],"Experiments":[168],"on":[169],"corpora":[172],"show":[173],"that":[174],"our":[175],"approach":[176],"can":[177],"produce":[178],"more":[179,191],"natural":[180],"speech":[181],"much":[183],"richer":[184],"variations,":[186],"superior":[192],"in":[193],"modeling":[194],"expressivity.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}