{"id":"https://openalex.org/W7148299358","doi":"https://doi.org/10.1109/asru65441.2025.11433845","title":"SENSE models: an open source solution for multilingual and multimodal semantic-based tasks","display_name":"SENSE models: an open source solution for multilingual and multimodal semantic-based tasks","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148299358","doi":"https://doi.org/10.1109/asru65441.2025.11433845"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11433845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132800606","display_name":"Salima Mdhaffar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Salima Mdhaffar","raw_affiliation_strings":["Avignon Université,LIA,Avignon,France"],"affiliations":[{"raw_affiliation_string":"Avignon Université,LIA,Avignon,France","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092596246","display_name":"Haroun Elleuch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Haroun Elleuch","raw_affiliation_strings":["Elyadata LIA/Avignon Université,Tunis,Tunisia"],"affiliations":[{"raw_affiliation_string":"Elyadata LIA/Avignon Université,Tunis,Tunisia","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128645679","display_name":"Chaimae Chellaf","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]},{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chaimae Chellaf","raw_affiliation_strings":["Lundi Matin LIA/Avignon Université,Avignon,France"],"affiliations":[{"raw_affiliation_string":"Lundi Matin LIA/Avignon Université,Avignon,France","institution_ids":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132814125","display_name":"Ha Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ha Nguyen","raw_affiliation_strings":["Oracle,France"],"affiliations":[{"raw_affiliation_string":"Oracle,France","institution_ids":["https://openalex.org/I1342911587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132824222","display_name":"Yannick Est\u00e8ve","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yannick Est\u00e8ve","raw_affiliation_strings":["Avignon Université,LIA,Avignon,France"],"affiliations":[{"raw_affiliation_string":"Avignon Université,LIA,Avignon,France","institution_ids":["https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5132800606"],"corresponding_institution_ids":["https://openalex.org/I4210119991"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92936107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20919999480247498,"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/T10028","display_name":"Topic Modeling","score":0.20919999480247498,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1843000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.17579999566078186,"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/utterance","display_name":"Utterance","score":0.6114000082015991},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6047999858856201},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5853999853134155},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5476999878883362},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4077000021934509},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.37689998745918274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919999957084656},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5501999855041504},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49939998984336853},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11433845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8077892661094666,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329605","display_name":"Avignon Universit\u00e9","ror":"https://ror.org/00mfpxb84"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2945700568","https://openalex.org/W3001434439","https://openalex.org/W3039695075","https://openalex.org/W3049256661","https://openalex.org/W3097777922","https://openalex.org/W3100460087","https://openalex.org/W3119308075","https://openalex.org/W3122349645","https://openalex.org/W3196509775","https://openalex.org/W3197771105","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W3214298066","https://openalex.org/W4283749766","https://openalex.org/W4286359908","https://openalex.org/W4319862446","https://openalex.org/W4319862635","https://openalex.org/W4375869259","https://openalex.org/W4385822293","https://openalex.org/W4386576685","https://openalex.org/W4399757539","https://openalex.org/W4402112187","https://openalex.org/W4402670856","https://openalex.org/W4402671401","https://openalex.org/W4406385636","https://openalex.org/W7131792756","https://openalex.org/W7131830571"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"SENSE":[3,83,95,115],"(Shared":[4],"Embedding":[5],"for":[6,79],"Nlingual":[7],"Speech":[8],"and":[9,19,70,81,92,109],"tExt),":[10],"an":[11],"open-source":[12],"solution":[13],"inspired":[14],"by":[15,63],"the":[16,41,50,56,89,93],"SAMUXLSR":[17],"framework":[18,33],"conceptually":[20],"similar":[21],"to":[22,34],"Meta":[23],"AI\u2019s":[24],"SONAR":[25],"models.":[26],"These":[27],"approaches":[28],"rely":[29],"on":[30,107],"a":[31,36,46,65,71],"teacher-student":[32],"align":[35],"self-supervised":[37],"speech":[38,74,136],"encoder":[39,48],"with":[40],"language-agnostic":[42],"continuous":[43],"representations":[44],"of":[45],"text":[47,68],"at":[49],"utterance":[51],"level.":[52],"We":[53,103],"describe":[54],"how":[55,128],"original":[57],"SAMU-XLSR":[58],"method":[59],"has":[60,85,99],"been":[61,86,100],"updated":[62],"selecting":[64],"stronger":[66],"teacher":[67],"model":[69,96,116],"better":[72],"initial":[73],"encoder.":[75],"The":[76],"source":[77],"code":[78],"training":[80],"using":[82],"models":[84],"integrated":[87],"into":[88,127],"SpeechBrain":[90],"toolkit,":[91],"first":[94],"we":[97],"trained":[98],"publicly":[101],"released.":[102],"report":[104],"experimental":[105],"results":[106],"multilingual":[108],"multimodal":[110],"semantic":[111],"tasks,":[112],"where":[113],"our":[114],"achieves":[117],"highly":[118],"competitive":[119],"performance.":[120],"Finally,":[121],"this":[122],"study":[123],"offers":[124],"new":[125],"insights":[126],"semantics":[129],"are":[130],"captured":[131],"in":[132],"such":[133],"semantically":[134],"aligned":[135],"encoders.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}