{"id":"https://openalex.org/W4408353462","doi":"https://doi.org/10.1109/icassp49660.2025.10888883","title":"SSE: A Speaking Style Extractor Based on Fine-Grained Contrastive Learning between Speech and Descriptive Text","display_name":"SSE: A Speaking Style Extractor Based on Fine-Grained Contrastive Learning between Speech and Descriptive Text","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353462","doi":"https://doi.org/10.1109/icassp49660.2025.10888883"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5036056631","display_name":"Zixing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023690509","display_name":"Yimeng Wu","orcid":"https://orcid.org/0000-0001-8278-8687"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimeng Wu","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104298357","display_name":"Zhongren Dong","orcid":"https://orcid.org/0000-0001-8074-1746"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongren Dong","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111047178","display_name":"W. W. Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wulong Xiang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594429","display_name":"Shengfan Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengfan Shen","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Imperial College London,GLAM,Department of Computing,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9171000123023987,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9171000123023987,"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/extractor","display_name":"Extractor","score":0.7882285118103027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7525537014007568},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.7256268262863159},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5873031616210938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4478156566619873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43042320013046265},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38312727212905884},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09509989619255066},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06981179118156433},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.05419352650642395}],"concepts":[{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.7882285118103027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525537014007568},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7256268262863159},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5873031616210938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478156566619873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43042320013046265},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38312727212905884},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09509989619255066},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06981179118156433},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.05419352650642395},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W942963634","https://openalex.org/W2057563799","https://openalex.org/W2146334809","https://openalex.org/W2513507089","https://openalex.org/W2742542661","https://openalex.org/W2794511405","https://openalex.org/W2963686995","https://openalex.org/W3030163527","https://openalex.org/W3081192838","https://openalex.org/W3127686677","https://openalex.org/W3138598836","https://openalex.org/W3161639065","https://openalex.org/W3162890625","https://openalex.org/W3207346153","https://openalex.org/W4206713267","https://openalex.org/W4226442948","https://openalex.org/W4372260310","https://openalex.org/W4372260512","https://openalex.org/W4375868872","https://openalex.org/W4375869257","https://openalex.org/W4375869379","https://openalex.org/W4382935150","https://openalex.org/W4385151928","https://openalex.org/W4391530692","https://openalex.org/W4392490330","https://openalex.org/W4392903203","https://openalex.org/W4392931281","https://openalex.org/W4402669711","https://openalex.org/W4402683976","https://openalex.org/W6766673545","https://openalex.org/W6779192484"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W1979583797","https://openalex.org/W2016864125","https://openalex.org/W2372254676","https://openalex.org/W2356229341","https://openalex.org/W2080135837","https://openalex.org/W2793679056","https://openalex.org/W4283332091","https://openalex.org/W3145050838","https://openalex.org/W2349768204"],"abstract_inverted_index":{"Effective":[0],"extraction":[1,89,104],"of":[2,26,52,61,90,105,118,125,129],"paralinguistic":[3,27,62,107,153],"features":[4],"from":[5],"speech,":[6],"such":[7,155],"as":[8,156,184],"emotion,":[9,157],"accent,":[10,161],"and":[11,40,49,160],"age,":[12],"remains":[13],"a":[14,79,86,137,185],"challenging":[15],"task":[16],"in":[17,47,64,127,166,170],"speech":[18,53,91,190],"processing.":[19],"Traditional":[20],"methods":[21],"typically":[22],"address":[23,69],"each":[24],"type":[25],"information":[28],"with":[29,121],"separate":[30],"classification":[31],"or":[32],"regression":[33],"tasks\u2014e.":[34],"g.,":[35],"emotion":[36],"recognition,":[37],"accent":[38],"detection,":[39],"age":[41],"estimation.":[42],"These":[43],"approaches":[44],"can":[45],"result":[46],"fragmented":[48],"incomplete":[50],"descriptions":[51,169],"style,":[54],"failing":[55],"to":[56,84,146,162],"capture":[57],"the":[58,74,103,113,130,164,189],"full":[59],"range":[60],"attributes":[63],"an":[65,96,122],"integrated":[66],"way.":[67],"To":[68],"these":[70],"limitations,":[71],"we":[72],"propose":[73,136],"Speech":[75],"Style":[76],"Extractor":[77],"(SSE),":[78],"novel":[80],"approach":[81,111],"that":[82],"aims":[83],"provide":[85],"more":[87],"comprehensive":[88],"style":[92,168],"features.":[93,108],"SSE":[94],"leverages":[95],"optimized":[97],"fine-grained":[98],"contrastive":[99],"learning":[100],"scheme,":[101],"enhancing":[102],"diverse":[106],"The":[109],"optimization":[110],"outperforms":[112],"baseline":[114],"on":[115],"11":[116],"out":[117],"13":[119],"datasets,":[120],"average":[123],"improvement":[124],"2.1%":[126],"terms":[128],"R@1":[131],"evaluation":[132],"metric.":[133],"We":[134],"also":[135,182],"complete":[138],"data":[139],"generation":[140],"framework":[141],"using":[142],"large":[143],"language":[144],"models":[145],"create":[147],"199k":[148],"text":[149],"samples":[150],"across":[151],"9":[152],"categories,":[154],"deception,":[158],"stuttering,":[159],"fill":[163],"gap":[165],"speaking":[167],"public":[171],"datasets.":[172],"This":[173],"extensive":[174],"dataset":[175],"not":[176],"only":[177],"facilitates":[178],"our":[179],"research":[180],"but":[181],"serves":[183],"valuable":[186],"resource":[187],"for":[188],"processing":[191],"community.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}