{"id":"https://openalex.org/W4416799571","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249141","title":"Conversation Context-Aware Direct Preference Optimization for Style-Controlled Speech Synthesis","display_name":"Conversation Context-Aware Direct Preference Optimization for Style-Controlled Speech Synthesis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799571","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249141"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5115912838","display_name":"Atsushi Kojima","orcid":null},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atsushi Kojima","raw_affiliation_strings":["SB Intuitions,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SB Intuitions,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["SB Intuitions,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SB Intuitions,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627106","display_name":"Hao Shi","orcid":"https://orcid.org/0000-0003-0184-2245"},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Shi","raw_affiliation_strings":["SB Intuitions,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SB Intuitions,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008935760","display_name":"Tomoya Mizumoto","orcid":null},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomoya Mizumoto","raw_affiliation_strings":["SB Intuitions,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SB Intuitions,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087402627","display_name":"Mengjie Zhao","orcid":"https://orcid.org/0000-0002-5544-8721"},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengjie Zhao","raw_affiliation_strings":["SB Intuitions,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SB Intuitions,Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["SB Intuitions,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SB Intuitions,Japan","institution_ids":["https://openalex.org/I88773910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I88773910"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3399827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"573","last_page":"578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9193999767303467,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9193999767303467,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.03920000046491623,"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":0.006399999838322401,"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/paralanguage","display_name":"Paralanguage","score":0.782800018787384},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6420999765396118},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6365000009536743},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5468000173568726},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.43059998750686646},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4278999865055084}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.782800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6488000154495239},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6420999765396118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.638700008392334},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.322299987077713},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1534131679","https://openalex.org/W1732078120","https://openalex.org/W2183341477","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2982568434","https://openalex.org/W3096147072","https://openalex.org/W3140429000","https://openalex.org/W3209059054","https://openalex.org/W4221163454","https://openalex.org/W4385822427","https://openalex.org/W4385823169","https://openalex.org/W4391454536","https://openalex.org/W4392902952","https://openalex.org/W4392974949","https://openalex.org/W4402115961","https://openalex.org/W4408354728","https://openalex.org/W4412886823"],"related_works":[],"abstract_inverted_index":{"Conversational":[0],"text-to-speech":[1],"(TTS)":[2],"generates":[3],"context-appropriate":[4],"expressive":[5],"speech":[6,80],"by":[7,70,97],"modeling":[8],"dialogue":[9],"context,":[10,95],"without":[11],"requiring":[12],"manual":[13],"paralinguistic":[14],"labels":[15],"such":[16],"as":[17],"emotion":[18,147],"or":[19],"intent.":[20],"However,":[21],"acoustically":[22],"similar":[23],"emotions":[24,131],"(e.g.,":[25],"happy":[26],"vs.":[27,154],"angry)":[28],"often":[29],"cause":[30],"inappropriate":[31,130],"renderings.":[32],"To":[33],"address":[34],"this,":[35],"we":[36,53],"propose":[37],"a":[38,60,85,98],"preference-based":[39,143],"optimization":[40,57,144],"approach":[41,165],"that":[42,142,163],"reinforces":[43],"the":[44,108,133,138],"model":[45,87,110],"toward":[46],"selecting":[47],"contextually":[48],"appropriate":[49,128],"emotional":[50,68,170],"expressions.":[51],"Specifically,":[52],"adopt":[54],"direct":[55],"preference":[56],"(DPO)":[58],"in":[59,104,177],"unit-based":[61,99],"TTS":[62],"architecture,":[63],"enabling":[64],"fine-grained":[65,167],"supervision":[66],"of":[67,169],"expression":[69,171],"comparing":[71],"discrete":[72,89],"unit":[73,125],"sequences":[74],"for":[75],"more":[76],"and":[77,94,172],"less":[78],"suitable":[79],"samples.":[81],"Our":[82],"method":[83],"employs":[84],"text-to-unit":[86,109],"predicting":[88],"acoustic":[90],"units":[91],"from":[92],"phonemes":[93],"followed":[96],"HiFi-GAN":[100],"vocoder.":[101],"Training":[102],"proceeds":[103],"two":[105],"stages:":[106],"first,":[107],"is":[111,122],"optimized":[112],"with":[113,152,157],"cross-entropy":[114],"(CE)":[115],"loss":[116],"on":[117,137],"ground-truth":[118],"units;":[119],"second,":[120],"DPO":[121],"applied":[123],"using":[124],"pairs":[126],"reflecting":[127],"versus":[129],"within":[132],"same":[134],"context.":[135],"Experiments":[136],"STUDIES":[139],"dataset":[140],"show":[141],"substantially":[145],"improves":[146],"recognition":[148],"accuracy":[149],"(67.14":[150],"%":[151,156],"CE+DPO":[153],"48.45":[155],"CE":[158],"only).":[159],"These":[160],"results":[161],"demonstrate":[162],"our":[164],"enables":[166],"control":[168],"better":[173],"captures":[174],"subtle":[175],"distinctions":[176],"conversational":[178],"speech.":[179]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}