{"id":"https://openalex.org/W4392902952","doi":"https://doi.org/10.1109/icassp48485.2024.10446506","title":"Concss: Contrastive-based Context Comprehension for Dialogue-Appropriate Prosody in Conversational Speech Synthesis","display_name":"Concss: Contrastive-based Context Comprehension for Dialogue-Appropriate Prosody in Conversational Speech Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902952","doi":"https://doi.org/10.1109/icassp48485.2024.10446506"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5008597430","display_name":"Yayue Deng","orcid":"https://orcid.org/0009-0003-7642-4942"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayue Deng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033565985","display_name":"Jinlong Xue","orcid":"https://orcid.org/0009-0000-0442-0932"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Xue","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002689662","display_name":"Yukang Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I51296178","display_name":"China Center of Advanced Science and Technology","ror":"https://ror.org/02egfyg20","country_code":"CN","type":"facility","lineage":["https://openalex.org/I102398690","https://openalex.org/I4210122102","https://openalex.org/I51296178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukang Jia","raw_affiliation_strings":["Perfect World Co., Ltd,Beijing,China","Perfect World Co., Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Perfect World Co., Ltd,Beijing,China","institution_ids":["https://openalex.org/I51296178"]},{"raw_affiliation_string":"Perfect World Co., Ltd, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101231780","display_name":"Qifei Li","orcid":"https://orcid.org/0009-0007-0422-6532"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qifei Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031705836","display_name":"Yichen Han","orcid":"https://orcid.org/0009-0008-7018-8949"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Han","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419335","display_name":"Fengping Wang","orcid":"https://orcid.org/0009-0001-4420-4553"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengping Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033063238","display_name":"Yingming Gao","orcid":"https://orcid.org/0000-0001-5881-3723"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingming Gao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8328,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86707061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10706","last_page":"10710"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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":0.9990000128746033,"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/prosody","display_name":"Prosody","score":0.8245990872383118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8008174896240234},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6122768521308899},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6041494607925415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5355019569396973},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.47418174147605896},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45694857835769653},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45102590322494507},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36661189794540405}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8245990872383118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008174896240234},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6122768521308899},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6041494607925415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5355019569396973},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.47418174147605896},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45694857835769653},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45102590322494507},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36661189794540405},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1021627522","display_name":null,"funder_award_id":"No. 2023RC13","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2217149964","display_name":null,"funder_award_id":"2023RC73","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2249315591","display_name":null,"funder_award_id":"62271083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7136399700","display_name":null,"funder_award_id":"2023RC13","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2097615438","https://openalex.org/W2157364932","https://openalex.org/W2187089797","https://openalex.org/W2394990819","https://openalex.org/W2964243274","https://openalex.org/W2978563181","https://openalex.org/W3151309757","https://openalex.org/W3195592874","https://openalex.org/W4221159457","https://openalex.org/W4225300652","https://openalex.org/W4226230180","https://openalex.org/W4240592325","https://openalex.org/W4283067649","https://openalex.org/W4304013787","https://openalex.org/W4320813209","https://openalex.org/W4366460484","https://openalex.org/W4372260474","https://openalex.org/W4375868859","https://openalex.org/W4385245566","https://openalex.org/W6755207826","https://openalex.org/W6778823374","https://openalex.org/W6796464841","https://openalex.org/W6849814592","https://openalex.org/W6851724922"],"related_works":["https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W187117048","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520","https://openalex.org/W2750037515","https://openalex.org/W4319862652","https://openalex.org/W2394249171"],"abstract_inverted_index":{"Conversational":[0],"speech":[1,15,130],"synthesis":[2],"(CSS)":[3],"incorporates":[4],"historical":[5],"dialogue":[6],"as":[7],"supplementary":[8],"information":[9],"with":[10,121],"the":[11,65,77,98,128],"aim":[12],"of":[13],"generating":[14],"that":[16,63,127],"has":[17],"dialogue-appropriate":[18],"prosody.":[19,141],"While":[20],"previous":[21],"methods":[22],"have":[23],"already":[24],"delved":[25],"into":[26,105],"enhancing":[27],"context":[28,30,79,93],"comprehension,":[29],"representation":[31,35],"still":[32],"lacks":[33],"effective":[34],"capabilities":[36],"and":[37,116,139],"context-sensitive":[38],"discriminability.":[39,95],"In":[40],"this":[41,52],"paper,":[42],"we":[43,54,82],"introduce":[44,83],"a":[45,84],"contrastive":[46,103,113],"learning-based":[47],"CSS":[48,62,123],"framework,":[49,53],"CONCSS.":[50],"Within":[51],"define":[55],"an":[56],"innovative":[57],"pretext":[58],"task":[59],"specific":[60],"to":[61,67,75,91,101],"enables":[64],"model":[66],"perform":[68],"self-supervised":[69],"learning":[70,104,114],"on":[71,111],"unlabeled":[72],"conversational":[73],"datasets":[74],"boost":[76],"model\u2019s":[78],"understanding.":[80],"Additionally,":[81],"sampling":[85],"strategy":[86],"for":[87],"negative":[88],"sample":[89],"augmentation":[90],"enhance":[92],"vectors\u2019":[94],"This":[96],"is":[97],"first":[99],"attempt":[100],"integrate":[102],"CSS.":[106],"We":[107],"conduct":[108],"ablation":[109],"studies":[110],"different":[112],"strategies":[115],"comprehensive":[117],"experiments":[118],"in":[119],"comparison":[120],"prior":[122],"systems.":[124],"Results":[125],"demonstrate":[126],"synthesized":[129],"from":[131],"our":[132],"proposed":[133],"method":[134],"exhibits":[135],"more":[136],"contextually":[137],"appropriate":[138],"sensitive":[140]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
