{"id":"https://openalex.org/W3198152857","doi":"https://doi.org/10.21437/interspeech.2021-412","title":"Controllable Context-Aware Conversational Speech Synthesis","display_name":"Controllable Context-Aware Conversational Speech Synthesis","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198152857","doi":"https://doi.org/10.21437/interspeech.2021-412","mag":"3198152857"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5064364353","display_name":"Jian Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cong","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685461","display_name":"Na Hu","orcid":"https://orcid.org/0000-0001-6362-0969"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Hu","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062105912","display_name":"Guangzhi Li","orcid":"https://orcid.org/0009-0004-9197-7737"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhi Li","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.099,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89430412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4658","last_page":"4662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9925000071525574,"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":0.9925000071525574,"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":0.9789999723434448,"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":0.974399983882904,"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":0.7831040620803833},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7518839836120605},{"id":"https://openalex.org/keywords/entrainment","display_name":"Entrainment (biomusicology)","score":0.6272274851799011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6064110398292542},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5439380407333374},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5395824313163757},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5065644979476929},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4145488440990448},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4042171239852905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3320656418800354},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12896299362182617},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10148343443870544},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08689230680465698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831040620803833},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7518839836120605},{"id":"https://openalex.org/C139992725","wikidata":"https://www.wikidata.org/wiki/Q5380656","display_name":"Entrainment (biomusicology)","level":3,"score":0.6272274851799011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6064110398292542},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5439380407333374},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5395824313163757},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5065644979476929},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4145488440990448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4042171239852905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3320656418800354},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12896299362182617},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10148343443870544},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08689230680465698},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","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.2021-412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2043003570","https://openalex.org/W2102003408","https://openalex.org/W2154920538","https://openalex.org/W2183470532","https://openalex.org/W2395956841","https://openalex.org/W2591927543","https://openalex.org/W2794490148","https://openalex.org/W2892140764","https://openalex.org/W2896457183","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2937881934","https://openalex.org/W2952127920","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015922793","https://openalex.org/W3095588618","https://openalex.org/W3097538987","https://openalex.org/W3113076898","https://openalex.org/W3142087749","https://openalex.org/W3146550708","https://openalex.org/W3151309757","https://openalex.org/W4295731579","https://openalex.org/W4298580827"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W1527532029","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2772323916","https://openalex.org/W2281307425","https://openalex.org/W1511346092","https://openalex.org/W2464405057"],"abstract_inverted_index":{"In":[0],"spoken":[1],"conversations,":[2,30],"spontaneous":[3,36,55,188],"behaviors":[4,56,78,189],"like":[5],"filled":[6],"pause":[7],"and":[8,58,64,141,182],"prolongations":[9],"always":[10],"happen.Conversational":[11],"partner":[12],"tends":[13],"to":[14,41,51,71,89,105,121,145,159],"align":[15],"features":[16],"of":[17,75,94,135,186],"their":[18,21],"speech":[19,38,100,110,130],"with":[20],"interlocutor":[22],"which":[23],"is":[24],"known":[25],"as":[26],"entrainment.To":[27],"produce":[28],"human-like":[29],"we":[31,47,115,152],"propose":[32],"a":[33,66,117,123,150,154],"unified":[34],"controllable":[35],"conversational":[37],"synthesis":[39],"framework":[40],"model":[42,63,108],"the":[43,61,73,76,87,91,95,98,109,128,133,139,146,161,165,170,184,187],"above":[44],"two":[45,53,77],"phenomena.Specifically,":[46],"use":[48],"explicit":[49],"labels":[50],"represent":[52],"typical":[54],"filled-pause":[57],"prolongation":[59],"in":[60,149,164],"acoustic":[62,113,119,166],"develop":[65,82],"neural":[67],"network":[68],"based":[69,85],"predictor":[70,88],"predict":[72],"occurrences":[74,185],"from":[79,102,127],"text.We":[80],"subsequently":[81],"an":[83],"algorithm":[84],"on":[86,132],"control":[90,183],"occurrence":[92],"frequency":[93],"behaviors,":[96],"making":[97],"synthesized":[99],"vary":[101],"less":[103],"disfluent":[104],"more":[106],"disfluent.To":[107],"entrainment":[111],"at":[112],"level,":[114],"utilize":[116],"context":[118],"encoder":[120,167],"extract":[122],"global":[124],"style":[125],"embedding":[126],"previous":[129,142],"conditioning":[131],"synthesizing":[134],"current":[136,140],"speech.Furthermore,":[137],"since":[138],"utterances":[143],"belong":[144],"different":[147],"speakers":[148],"conversation,":[151],"add":[153],"domain":[155],"adversarial":[156],"training":[157],"module":[158],"eliminate":[160],"speaker-related":[162],"information":[163],"while":[168],"maintaining":[169],"style-related":[171],"information.Experiments":[172],"show":[173],"that":[174],"our":[175],"proposed":[176],"approach":[177],"can":[178],"synthesize":[179],"realistic":[180],"conversations":[181],"naturally.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}