{"id":"https://openalex.org/W4375869215","doi":"https://doi.org/10.1109/icassp49357.2023.10096268","title":"Improving Accented Speech Recognition with Multi-Domain Training","display_name":"Improving Accented Speech Recognition with Multi-Domain Training","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869215","doi":"https://doi.org/10.1109/icassp49357.2023.10096268"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04163554/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026288815","display_name":"Lucas Maison","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"]},{"id":"https://openalex.org/I4210140930","display_name":"Thales (France)","ror":"https://ror.org/04emwm605","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I4390039363","display_name":"Infection et inflammation","ror":"https://ror.org/021sh3243","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4390039363"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lucas Maison","raw_affiliation_strings":["Laboratoire Informatique D’Avignon,Avignon,France","Thales SIX GTS France (92230 Gennevilliers - 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":"Laboratoire Informatique D’Avignon,Avignon,France","institution_ids":["https://openalex.org/I4210119991","https://openalex.org/I4390039363"]},{"raw_affiliation_string":"Thales SIX GTS France (92230 Gennevilliers - France)","institution_ids":["https://openalex.org/I4210140930"]},{"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"]},{"id":"https://openalex.org/I4390039363","display_name":"Infection et inflammation","ror":"https://ror.org/021sh3243","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4390039363"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yannick Esteve","raw_affiliation_strings":["Laboratoire Informatique D’Avignon,Avignon,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":"Laboratoire Informatique D’Avignon,Avignon,France","institution_ids":["https://openalex.org/I4210119991","https://openalex.org/I4390039363"]},{"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8030179738998413},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.73580402135849},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7273570895195007},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6800618171691895},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5349477529525757},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.506192147731781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019741058349609},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4885450303554535},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4566246271133423},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4510582387447357},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4233981966972351},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.415643572807312},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35970520973205566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3470468521118164},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.19829240441322327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08062303066253662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030179738998413},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.73580402135849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7273570895195007},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6800618171691895},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5349477529525757},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.506192147731781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019741058349609},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4885450303554535},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4566246271133423},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4510582387447357},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4233981966972351},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.415643572807312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35970520973205566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3470468521118164},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.19829240441322327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08062303066253662},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04163554v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04163554","pdf_url":"https://hal.science/hal-04163554/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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10096268⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04163554v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04163554","pdf_url":"https://hal.science/hal-04163554/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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10096268⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375869215.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W120265440","https://openalex.org/W1522301498","https://openalex.org/W2099621636","https://openalex.org/W2810556878","https://openalex.org/W2888797456","https://openalex.org/W2936774411","https://openalex.org/W2972848589","https://openalex.org/W2973094925","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3167533889","https://openalex.org/W3197008493","https://openalex.org/W3198270883","https://openalex.org/W3198771897","https://openalex.org/W3207583491","https://openalex.org/W4283073456","https://openalex.org/W4318151426","https://openalex.org/W4319862480","https://openalex.org/W6631190155","https://openalex.org/W6675409298","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6802472062","https://openalex.org/W6849142062"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2531741693","https://openalex.org/W2146197305","https://openalex.org/W2134950286"],"abstract_inverted_index":{"Thanks":[0],"to":[1,33,51,90,99],"the":[2,57,68],"rise":[3],"of":[4,21,59],"self-supervised":[5],"learning,":[6],"automatic":[7],"speech":[8,44],"recognition":[9],"(ASR)":[10],"systems":[11],"now":[12],"achieve":[13],"near":[14],"human":[15],"performance":[16,106],"on":[17,93,107],"a":[18,104],"wide":[19],"variety":[20],"datasets.":[22],"However,":[23],"they":[24],"still":[25],"lack":[26],"generalization":[27],"capability":[28],"and":[29,75,95],"are":[30],"not":[31],"robust":[32],"domain":[34],"shifts":[35],"like":[36],"accent":[37],"variations.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,71,83],"use":[43],"audio":[45],"representing":[46],"four":[47],"different":[48],"French":[49],"accents":[50,66,97],"create":[52],"fine-tuning":[53],"datasets":[54],"that":[55,82],"improve":[56],"robustness":[58],"pre-trained":[60],"ASR":[61],"models.":[62],"By":[63],"incorporating":[64],"various":[65],"in":[67],"training":[69,101],"set,":[70],"obtain":[72],"both":[73],"in-domain":[74],"out-of-domain":[76],"improvements.":[77],"Our":[78],"numerical":[79],"experiments":[80],"show":[81],"can":[84],"reduce":[85],"error":[86],"rates":[87],"by":[88],"up":[89],"25%":[91],"(relative)":[92],"African":[94],"Belgian":[96],"compared":[98],"single-domain":[100],"while":[102],"keeping":[103],"good":[105],"standard":[108],"French.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}