{"id":"https://openalex.org/W4392904607","doi":"https://doi.org/10.1109/icassp48485.2024.10448356","title":"Considering Temporal Connection between Turns for Conversational Speech Synthesis","display_name":"Considering Temporal Connection between Turns for Conversational Speech Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904607","doi":"https://doi.org/10.1109/icassp48485.2024.10448356"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448356","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":"conference-paper","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/A5029135332","display_name":"Kangdi Mei","orcid":null},"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":"Kangdi Mei","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078812627","display_name":"Zhaoci Liu","orcid":null},"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":"Zhaoci Liu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"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":"Huipeng Du","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780078","display_name":"Hengyu Li","orcid":"https://orcid.org/0000-0002-2243-5908"},"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":"Hengyu Li","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"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":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430197","display_name":"Liping Chen","orcid":"https://orcid.org/0000-0003-1902-0215"},"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":"Liping Chen","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. 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":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11426","last_page":"11430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.983299970626831,"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":0.7999147176742554},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7471874356269836},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6052887439727783},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5592716932296753},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5444565415382385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.531197726726532},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5031208395957947},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5027718544006348},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4783365726470947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3278898000717163},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10414063930511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999147176742554},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7471874356269836},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6052887439727783},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5592716932296753},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5444565415382385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.531197726726532},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5031208395957947},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5027718544006348},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4783365726470947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3278898000717163},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10414063930511475},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448356","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":[],"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":25,"referenced_works":["https://openalex.org/W2395956841","https://openalex.org/W2896457183","https://openalex.org/W2973177710","https://openalex.org/W2979476256","https://openalex.org/W3015282541","https://openalex.org/W3033411150","https://openalex.org/W3115920274","https://openalex.org/W3151309757","https://openalex.org/W3174758275","https://openalex.org/W3196027980","https://openalex.org/W3198152857","https://openalex.org/W3198217962","https://openalex.org/W3216976702","https://openalex.org/W4225300652","https://openalex.org/W4296068977","https://openalex.org/W4307680525","https://openalex.org/W4372341043","https://openalex.org/W4377000449","https://openalex.org/W4382202703","https://openalex.org/W4385245566","https://openalex.org/W6603931906","https://openalex.org/W6749555683","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6852750031"],"related_works":["https://openalex.org/W566641833","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148"],"abstract_inverted_index":{"Conversational":[0],"speech":[1,6,20,52],"synthesis":[2,21,26],"aims":[3],"to":[4,105],"synthesize":[5],"of":[7,28,40,62,110,138,146,156,178],"an":[8,89],"individual":[9],"speaker":[10],"based":[11,124],"on":[12,24,125,169],"history":[13,81],"conversation.":[14],"However,":[15],"most":[16],"studies":[17],"in":[18,70,186],"conversational":[19,51],"only":[22,79,112],"focus":[23],"the":[25,29,35,45,58,107,117,129,143,154,170,176],"performance":[27,168],"current":[30,113],"speaker\u2019s":[31],"turn":[32,82,104,114,140],"and":[33,60,78,99,127,133,160,175],"neglect":[34],"temporal":[36,46,171],"relationship":[37],"between":[38,48,76,173],"turns":[39,49,77,174],"interlocutors.":[41],"Therefore,":[42],"we":[43],"consider":[44],"connection":[47,172],"for":[50,57],"synthesis,":[53],"which":[54,71,94],"is":[55,73,83,92,122],"crucial":[56],"naturalness":[59],"coherence":[61],"conversations.":[63],"Specifically,":[64],"this":[65,87],"paper":[66],"formulates":[67],"a":[68],"task":[69],"there":[72],"no":[74],"overlap":[75],"one":[80],"considered.":[84],"To":[85],"complete":[86],"task,":[88],"acoustic":[90,108,131,144,158],"model":[91,121,165],"proposed":[93],"leverages":[95],"multi-modal":[96],"(including":[97],"text":[98],"speech)":[100],"information":[101,159],"from":[102],"previous":[103,139],"predict":[106],"features":[109,145],"not":[111],"but":[115],"also":[116],"inter-turn":[118],"gap.":[119],"The":[120],"designed":[123],"MQTTS":[126],"incorporates":[128],"global":[130,157],"representation":[132,137],"BERT-based":[134],"local":[135,161],"semantic":[136,162],"when":[141],"predicting":[142],"each":[147],"frame.":[148],"Experimental":[149],"results":[150],"demonstrate":[151],"that":[152],"with":[153],"introduction":[155],"information,":[163],"our":[164],"achieves":[166],"better":[167],"quality":[177],"synthetic":[179],"speech.":[180],"Audio":[181],"samples":[182],"can":[183],"be":[184],"found":[185],"https://mkd-mkd.github.io/icassp2024.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}