{"id":"https://openalex.org/W4416799343","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248977","title":"Disfluency Disentanglement Enhancement in Spoken-Text-Style Transfer for Spontaneous Speech Synthesis","display_name":"Disfluency Disentanglement Enhancement in Spoken-Text-Style Transfer for Spontaneous Speech Synthesis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799343","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248977"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248977","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":null,"display_name":"Yuuto Nakata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142609","display_name":"National Institute of Technology, Tokuyama College","ror":"https://ror.org/046jx2h22","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210142609"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuuto Nakata","raw_affiliation_strings":["National Institute of Technology, Tokuyama College,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Tokuyama College,Japan","institution_ids":["https://openalex.org/I4210142609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084310192","display_name":"Daiki Yoshioka","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Yoshioka","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1764841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1098","last_page":"1103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8300999999046326,"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":0.8300999999046326,"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/T10863","display_name":"Voice and Speech Disorders","score":0.032999999821186066,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.02930000051856041,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/robustness","display_name":"Robustness (evolution)","score":0.5717999935150146},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5382999777793884},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.43380001187324524},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3747999966144562},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3287000060081482},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.31540000438690186},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.31439998745918274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330999970436096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6014000177383423},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5717999935150146},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5177000164985657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3747999966144562},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248977","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spoken-text-style":[0],"transfer":[1,107],"(STST)":[2],"aims":[3],"to":[4,9,58,69,80,116],"convert":[5],"a":[6,10,35,63,75,105],"given":[7],"text":[8],"desired":[11],"style":[12],"while":[13],"preserving":[14],"its":[15],"semantic":[16],"content.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,110],"focus":[22],"on":[23],"modeling":[24],"the":[25,59,82,94,100,112],"disfluency":[26,76,119],"in":[27,38,121],"spoken":[28],"text,":[29],"which":[30],"can":[31],"be":[32],"useful":[33],"as":[34],"preprocessing":[36],"step":[37],"spontaneous":[39],"speech":[40],"synthesis.":[41],"Previous":[42],"methods":[43],"suffer":[44],"from":[45],"unknown":[46,72,97],"words":[47],"and":[48,52,74,99],"confusion":[49],"between":[50],"normal":[51,85],"disfluent":[53],"words.":[54,86],"Our":[55],"proposed":[56],"solutions":[57],"above-mentioned":[60],"problems":[61],"include":[62],"masked":[64],"language":[65],"model":[66],"(MLM)":[67],"approach":[68],"temporally":[70],"replace":[71],"words,":[73,98],"symbol":[77],"representation":[78],"(DSR)":[79],"increase":[81],"discrepancy":[83],"against":[84,96],"Experimental":[87],"evaluation":[88],"results":[89],"show":[90,111],"that":[91],"MLM":[92],"improves":[93],"robustness":[95],"use":[101],"of":[102,114],"DSR":[103],"achieves":[104],"higher":[106],"accuracy.":[108],"Finally,":[109],"potential":[113],"speaker-modeling":[115],"achieve":[117],"speaker-wise":[118],"control":[120],"STST.":[122]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}