{"id":"https://openalex.org/W4405710078","doi":"https://doi.org/10.1109/iscslp63861.2024.10800061","title":"FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis","display_name":"FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405710078","doi":"https://doi.org/10.1109/iscslp63861.2024.10800061"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100708728","display_name":"Yifan Hu","orcid":"https://orcid.org/0009-0004-9393-5004"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Hu","raw_affiliation_strings":["Inner Mongolia University"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448651","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4308-645X"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Inner Mongolia University"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100708728"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70222911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9842000007629395,"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":0.9842000007629395,"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":0.9340000152587891,"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":0.8126462697982788},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5605167150497437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4581022262573242},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.441201776266098},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39582550525665283},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.04684633016586304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126462697982788},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5605167150497437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4581022262573242},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.441201776266098},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39582550525665283},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.04684633016586304},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G600008135","display_name":null,"funder_award_id":"62206136","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":34,"referenced_works":["https://openalex.org/W157389678","https://openalex.org/W1975163393","https://openalex.org/W2074042974","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2395956841","https://openalex.org/W2946085385","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2997771882","https://openalex.org/W2998432370","https://openalex.org/W3048768961","https://openalex.org/W3100110884","https://openalex.org/W3151309757","https://openalex.org/W3196001064","https://openalex.org/W3198152857","https://openalex.org/W4225275170","https://openalex.org/W4282030117","https://openalex.org/W4283662594","https://openalex.org/W4285301431","https://openalex.org/W4285553096","https://openalex.org/W4304013787","https://openalex.org/W4372260474","https://openalex.org/W4385245566","https://openalex.org/W4385822427","https://openalex.org/W4390926710","https://openalex.org/W6745297980","https://openalex.org/W6749489859","https://openalex.org/W6755207826","https://openalex.org/W6762339780","https://openalex.org/W6763832098","https://openalex.org/W6765987481","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Conversational":[0],"Text-to-Speech":[1],"(TTS)":[2],"aims":[3],"to":[4,35,113,161],"synthesis":[5],"an":[6,56,64,127],"utterance":[7,24,31,128],"with":[8],"the":[9,22,26,30,37,43,47,51,60,73,90,98,105,115,123,133,154,162,173],"right":[10],"linguistic":[11],"and":[12,25,92,109,117,129,148,165],"affective":[13],"prosody":[14],"in":[15,46,72],"a":[16,79,142],"conversational":[17,82],"context.":[18],"The":[19,146],"correlation":[20],"between":[21,126],"current":[23],"dialogue":[27,48,131,135,143],"history":[28,49],"at":[29,50,97],"level":[32,53],"was":[33],"used":[34],"improve":[36],"expressiveness":[38],"of":[39,63,141],"synthesized":[40],"speech.":[41,170],"However,":[42],"fine-grained":[44,134],"information":[45],"word":[52,116],"also":[54],"has":[55,67],"important":[57],"impact":[58],"on":[59,139],"prosodic":[61],"expression":[62],"utterance,":[65],"which":[66],"not":[68],"been":[69],"well":[70],"studied":[71],"prior":[74],"work.":[75],"Therefore,":[76],"we":[77],"propose":[78],"novel":[80],"expressive":[81,169],"TTS":[83],"model,":[84],"termed":[85],"as":[86],"FCTalker,":[87],"that":[88,153],"learns":[89],"fine":[91,108],"coarse":[93,110],"grained":[94,111],"context":[95,119],"dependency":[96],"same":[99],"time":[100],"during":[101],"speech":[102],"generation.":[103],"Specifically,":[104],"FCTalker":[106],"includes":[107],"encoders":[112],"exploit":[114],"utterance-level":[118],"dependency.":[120],"To":[121],"model":[122,156,164],"word-level":[124],"dependencies":[125],"its":[130],"history,":[132],"encoder":[136],"is":[137],"built":[138],"top":[140],"BERT":[144],"model.":[145],"subjective":[147],"objective":[149],"evaluation":[150],"results":[151,159],"show":[152],"proposed":[155],"achieves":[157],"remarkable":[158],"compared":[160],"baseline":[163],"generates":[166],"contextually":[167],"appropriate":[168],"We":[171],"release":[172],"source":[174],"code":[175],"at:":[176],"https://github.com/AI-S2-Lab/FCTalker.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}