{"id":"https://openalex.org/W4297841911","doi":"https://doi.org/10.21437/interspeech.2022-352","title":"ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks","display_name":"ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841911","doi":"https://doi.org/10.21437/interspeech.2022-352"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-352","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-352","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5060151795","display_name":"Valentin Pelloin","orcid":"https://orcid.org/0000-0002-1259-127X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Valentin Pelloin","raw_affiliation_strings":["Laboratoire d'Informatique de l'Universit\u00e9 du Mans (LIUM), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de l'Universit\u00e9 du Mans (LIUM), France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087255768","display_name":"Franck Dary","orcid":null},"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/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Franck Dary","raw_affiliation_strings":["Aix Marseille Univ, Universit\u00e9 de Toulon, CNRS, LIS, Marseille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix Marseille Univ, Universit\u00e9 de Toulon, CNRS, LIS, Marseille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I4210114274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102727799","display_name":"Nicolas Herv\u00e9","orcid":"https://orcid.org/0000-0002-2249-3710"},"institutions":[{"id":"https://openalex.org/I4210125774","display_name":"Institut National de l'Audiovisuel","ror":"https://ror.org/02zwkwz55","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210125774"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Herv\u00e9","raw_affiliation_strings":["Institut National de l'Audiovisuel (INA), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut National de l'Audiovisuel (INA), France","institution_ids":["https://openalex.org/I4210125774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071505335","display_name":"Beno\u00eet Favre","orcid":"https://orcid.org/0000-0002-9777-4613"},"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/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Favre","raw_affiliation_strings":["Aix Marseille Univ, Universit\u00e9 de Toulon, CNRS, LIS, Marseille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix Marseille Univ, Universit\u00e9 de Toulon, CNRS, LIS, Marseille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I4210114274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056103113","display_name":"Nathalie Camelin","orcid":"https://orcid.org/0000-0001-6786-1372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathalie Camelin","raw_affiliation_strings":["Laboratoire d'Informatique de l'Universit\u00e9 du Mans (LIUM), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de l'Universit\u00e9 du Mans (LIUM), France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine LAURENT","raw_affiliation_strings":["Laboratoire d'Informatique de l'Universit\u00e9 du Mans (LIUM), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de l'Universit\u00e9 du Mans (LIUM), France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040820339","display_name":"Laurent Besacier","orcid":"https://orcid.org/0000-0001-7411-9125"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent Besacier","raw_affiliation_strings":["Naver Labs Europe (NLE), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Labs Europe (NLE), France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060151795"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3453","last_page":"3457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9685999751091003,"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":0.9685999751091003,"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":0.9501000046730042,"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":0.9154000282287598,"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":0.834598183631897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5886589288711548},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5442885756492615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.526116669178009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.468894898891449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.834598183631897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5886589288711548},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5442885756492615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.526116669178009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.468894898891449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-352","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-352","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1663281917","display_name":"Artificial Intelligence foR Semantically controlled SPEech UndeRstanding","funder_award_id":"ANR-19-CE23-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6701594011","display_name":null,"funder_award_id":"ANR-19-CE23-0004-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W21503661","https://openalex.org/W163811496","https://openalex.org/W177378321","https://openalex.org/W595069947","https://openalex.org/W1524333225","https://openalex.org/W2035438624","https://openalex.org/W2137871902","https://openalex.org/W2150859660","https://openalex.org/W2250641567","https://openalex.org/W2250976578","https://openalex.org/W2620757702","https://openalex.org/W2896457183","https://openalex.org/W2963288440","https://openalex.org/W2965373594","https://openalex.org/W2986154550","https://openalex.org/W2990391581","https://openalex.org/W3015746101","https://openalex.org/W3015867372","https://openalex.org/W3024182269","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3095711142","https://openalex.org/W3096690837","https://openalex.org/W3126870998","https://openalex.org/W3139580003","https://openalex.org/W3169320628","https://openalex.org/W3185922486","https://openalex.org/W3188188945","https://openalex.org/W3203375531","https://openalex.org/W3212666042","https://openalex.org/W4205470935","https://openalex.org/W4287760320"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"aim":[1],"at":[2],"improving":[3],"spoken":[4,42,76,113],"language":[5,43,77,114],"modeling":[6],"(LM)":[7],"using":[8],"very":[9],"large":[10],"amount":[11],"of":[12,29,37,80],"automatically":[13],"transcribed":[14],"speech.We":[15],"leverage":[16],"the":[17,68],"INA":[18],"(French":[19],"National":[20],"Audiovisual":[21],"Institute":[22],"1":[23],")":[24,55],"collection":[25],"and":[26,70,83],"obtain":[27],"19GB":[28],"text":[30,107],"after":[31],"applying":[32],"ASR":[33],"on":[34],"350,000":[35],"hours":[36],"diverse":[38],"TV":[39,81],"shows.From":[40],"this,":[41],"models":[44,63],"are":[45,65],"trained":[46],"either":[47],"by":[48],"fine-tuning":[49],"an":[50],"existing":[51],"LM":[52,60],"(FlauBERT":[53],"2":[54],"or":[56],"through":[57],"training":[58],"a":[59],"from":[61],"scratch.New":[62],"(FlauBERT-Oral)":[64],"shared":[66],"with":[67],"community":[69],"evaluated":[71],"for":[72],"3":[73],"downstream":[74],"tasks:":[75],"understanding,":[78],"classification":[79],"shows":[82],"speech":[84],"syntactic":[85],"parsing.Results":[86],"show":[87],"that":[88],"FlauBERT-Oral":[89],"can":[90,108],"be":[91,109],"beneficial":[92],"compared":[93],"to":[94,111],"its":[95,102],"initial":[96],"FlauBERT":[97],"version":[98],"demonstrating":[99],"that,":[100],"despite":[101],"inherent":[103],"noisy":[104],"nature,":[105],"ASR-generated":[106],"used":[110],"build":[112],"models.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}