{"id":"https://openalex.org/W4385478173","doi":"https://doi.org/10.1109/icasspw59220.2023.10193452","title":"Specialized Semantic Enrichment of Speech Representations","display_name":"Specialized Semantic Enrichment of Speech Representations","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385478173","doi":"https://doi.org/10.1109/icasspw59220.2023.10193452"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193452","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/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":"G. Laperri\u00e8re","raw_affiliation_strings":["Avignon Université,LIA,France","LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avignon Université,LIA,France","institution_ids":["https://openalex.org/I4210119991"]},{"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/A5100635655","display_name":"Ha H. Nguyen","orcid":"https://orcid.org/0000-0001-6481-0422"},"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":"H. Nguyen","raw_affiliation_strings":["Avignon Université,LIA,France","LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avignon Université,LIA,France","institution_ids":["https://openalex.org/I4210119991"]},{"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/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"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":"S. Ghannay","raw_affiliation_strings":["Université Paris-Saclay,LISN - CNRS,France","STL - Sciences et Technologies des Langues - LISN (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay,LISN - CNRS,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]},{"raw_affiliation_string":"STL - Sciences et Technologies des Langues - LISN (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":"B. Jabaian","raw_affiliation_strings":["Avignon Université,LIA,France","LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avignon Université,LIA,France","institution_ids":["https://openalex.org/I4210119991"]},{"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/A5108854539","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":"Y. Est\u00e8ve","raw_affiliation_strings":["Avignon Université,LIA,France","LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avignon Université,LIA,France","institution_ids":["https://openalex.org/I4210119991"]},{"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":4,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.8853905200958252},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7524967193603516},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.685726523399353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5828597545623779},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5699400901794434},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5471226572990417},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.538682222366333},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4408491253852844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3441663384437561},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07940754294395447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8853905200958252},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7524967193603516},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.685726523399353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5828597545623779},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5699400901794434},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5471226572990417},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.538682222366333},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4408491253852844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3441663384437561},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07940754294395447},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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":2,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193452","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04425710v1","is_oa":false,"landing_page_url":"https://cnrs.hal.science/hal-04425710","pdf_url":null,"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":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSPW59220.2023.10193452⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W21503661","https://openalex.org/W204182981","https://openalex.org/W1649407914","https://openalex.org/W2249819665","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2914417638","https://openalex.org/W2963288440","https://openalex.org/W2970820898","https://openalex.org/W2972314145","https://openalex.org/W2972327934","https://openalex.org/W3015412890","https://openalex.org/W3015885816","https://openalex.org/W3016006013","https://openalex.org/W3029914199","https://openalex.org/W3036601975","https://openalex.org/W3039695075","https://openalex.org/W3098169801","https://openalex.org/W3122349645","https://openalex.org/W3148001440","https://openalex.org/W3197642003","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4225096077","https://openalex.org/W4226194717","https://openalex.org/W4286359908","https://openalex.org/W4305027257","https://openalex.org/W4319862446","https://openalex.org/W6755207826","https://openalex.org/W6778560980","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2375873920","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2392760275","https://openalex.org/W2597655663"],"abstract_inverted_index":{"SSL":[0,82,179],"is":[1,111],"now":[2],"commonly":[3],"used":[4],"to":[5,37,50,76,87,104,130,136,170],"capture":[6,38],"multilingual":[7,29,90],"speech":[8,14,83],"representation,":[9],"by":[10,142,176],"exploiting":[11,143],"huge":[12,28],"audio":[13],"data":[15,158],"in":[16,35,74,85,102,168],"several":[17],"languages.":[18],"In":[19,93,117],"parallel,":[20],"some":[21,89],"text-based":[22],"large":[23],"neural":[24],"models":[25],"trained":[26],"on":[27],"textual":[30],"documents":[31],"have":[32],"been":[33,65],"introduced":[34,66],"order":[36,75,86,103,169],"the":[39,47,54,78,154,172],"general":[40],"semantics":[41],"of":[42,46,56,70,80,147,156],"a":[43,57,94,99,114,131,137,144,160],"sentence,":[44],"independently":[45],"language,":[48],"and":[49],"represent":[51],"it":[52],"under":[53],"form":[55],"sentence":[58,72],"embedding.":[59],"Very":[60],"recently,":[61],"an":[62,81],"approach":[63],"has":[64],"that":[67,153],"takes":[68],"benefit":[69],"such":[71],"embedding":[73],"continue":[77],"training":[79],"model":[84,180],"inject":[88],"semantic":[91,109,125,173],"information.":[92],"previous":[95],"work,":[96],"we":[97,121],"made":[98],"layer-wise":[100],"analysis":[101],"better":[105],"understand":[106],"how":[107,123],"this":[108,118,124,177],"information":[110,126],"integrated":[112],"into":[113],"wav2vec2.0":[115],"model.":[116],"new":[119],"study,":[120],"show":[122,152],"can":[127,163],"be":[128,165],"specialized":[129],"targeted":[132],"downstream":[133],"task":[134],"dedicated":[135],"task-oriented":[138],"spoken":[139],"language":[140,162],"understanding":[141],"small":[145],"amount":[146],"transcribed":[148],"data.":[149],"We":[150],"also":[151,164],"use":[155],"in-domain":[157],"from":[159],"close":[161],"very":[166],"beneficial":[167],"make":[171],"representation":[174],"captured":[175],"enriched":[178],"more":[181],"accurate.":[182]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}