{"id":"https://openalex.org/W4399757558","doi":"https://doi.org/10.21437/interspeech.2024-1133","title":"A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding","display_name":"A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4399757558","doi":"https://doi.org/10.21437/interspeech.2024-1133"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1133","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.12141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089134789","display_name":"Ga\u00eblle Laperri\u00e8re","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":"Ga\u00eblle Laperri\u00e8re","raw_affiliation_strings":["LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000557257","display_name":"Sahar Ghannay","orcid":"https://orcid.org/0000-0002-7531-2522"},"institutions":[{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sahar Ghannay","raw_affiliation_strings":["LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507\r\nRue du Belv\u00e9d\u00e8re\r\n91405 Orsay cedex\r\net \r\nCampus Universitaire b\u00e2t 640\r\n1 rue Raimond Castaing\r\n91190 Gif-sur-Yvette - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507\r\nRue du Belv\u00e9d\u00e8re\r\n91405 Orsay cedex\r\net \r\nCampus Universitaire b\u00e2t 640\r\n1 rue Raimond Castaing\r\n91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084718063","display_name":"Bassam Jabaian","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":"Bassam Jabaian","raw_affiliation_strings":["LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081852717","display_name":"Yannick Est\u00e8ve","orcid":"https://orcid.org/0000-0002-3656-8883"},"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":["LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)","institution_ids":["https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"812","last_page":"816"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9936000108718872,"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":0.8889678716659546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6847727298736572},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6656436324119568},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6606698036193848},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5862781405448914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5785307288169861},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5777722597122192},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45611971616744995},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41326671838760376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3552504777908325},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12354198098182678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8889678716659546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6847727298736572},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6656436324119568},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6606698036193848},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5862781405448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5785307288169861},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5777722597122192},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45611971616744995},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41326671838760376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3552504777908325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12354198098182678},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2024-1133","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.12141","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12141","pdf_url":"https://arxiv.org/pdf/2406.12141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-04615074v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04615074","pdf_url":"https://hal.science/hal-04615074/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://interspeech2024.org/","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2406.12141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.12141","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.12141","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12141","pdf_url":"https://arxiv.org/pdf/2406.12141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1046731639","display_name":null,"funder_award_id":"101007666","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7331901853","display_name":null,"funder_award_id":"EU H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399757558.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W107105315","https://openalex.org/W4367156293","https://openalex.org/W1584537303","https://openalex.org/W4388155270","https://openalex.org/W1872724644","https://openalex.org/W2750549761","https://openalex.org/W28826848","https://openalex.org/W2122272819","https://openalex.org/W2130894091","https://openalex.org/W2994151208"],"abstract_inverted_index":{"Self-Supervised":[0],"Learning":[1],"is":[2],"vastly":[3],"used":[4],"to":[5,23,33,53,97,111],"efficiently":[6],"represent":[7],"speech":[8,36],"for":[9,120],"Spoken":[10],"Language":[11],"Understanding,":[12],"gradually":[13],"replacing":[14],"conventional":[15],"approaches.":[16],"Meanwhile,":[17],"textual":[18],"SSL":[19],"models":[20],"are":[21],"proposed":[22],"encode":[24],"language-agnostic":[25],"semantics.":[26],"SAMU-XLSR":[27,42,113],"framework":[28],"employed":[29],"this":[30,103],"semantic":[31,44,114],"information":[32],"enrich":[34],"multilingual":[35,69,121],"representations.":[37],"A":[38],"recent":[39],"study":[40],"investigated":[41],"in-domain":[43],"enrichment":[45,115],"by":[46,77],"specializing":[47],"it":[48],"on":[49,56],"downstream":[50],"transcriptions,":[51],"leading":[52],"state-of-the-art":[54],"results":[55],"a":[57,98,106],"challenging":[58],"SLU":[59,85,100],"task.":[60],"This":[61],"study's":[62],"interest":[63],"lies":[64],"in":[65,80],"the":[66],"loss":[67,91],"of":[68,73,92],"performances":[70],"and":[71,122],"lack":[72],"specific-semantics":[74],"training":[75],"induced":[76],"such":[78],"specialization":[79],"close":[81],"languages":[82,119],"without":[83],"any":[84],"implication.":[86],"We":[87],"also":[88],"consider":[89],"SAMU-XLSR's":[90],"initial":[93],"cross-lingual":[94],"abilities":[95],"due":[96],"separate":[99],"fine-tuning.":[101],"Therefore,":[102],"paper":[104],"proposes":[105],"dual":[107],"task":[108],"learning":[109],"approach":[110],"improve":[112],"while":[116],"considering":[117],"distant":[118],"language":[123],"portability":[124],"experiments.":[125]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2024-06-18T00:00:00"}
