{"id":"https://openalex.org/W3209109064","doi":"https://doi.org/10.48550/arxiv.2110.15731","title":"CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese","display_name":"CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese","publication_year":2021,"publication_date":"2021-10-14","ids":{"openalex":"https://openalex.org/W3209109064","doi":"https://doi.org/10.48550/arxiv.2110.15731","mag":"3209109064"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2110.15731","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15731","pdf_url":"https://arxiv.org/pdf/2110.15731","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,"listed_in":[],"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":"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.15731","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083987838","display_name":"Arnaldo C\u00e2ndido","orcid":"https://orcid.org/0000-0002-5647-0891","observed_orcids":["https://orcid.org/0000-0002-5647-0891"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junior, Arnaldo Candido","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025318789","display_name":"Edresson Casanova","orcid":"https://orcid.org/0000-0003-0160-7173","observed_orcids":["https://orcid.org/0000-0003-0160-7173"]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Casanova, Edresson","raw_affiliation_strings":["Instituto de Ci\u00eancias Matem\u00e1ticas e de Computac \u00b8\u00e3o , University of S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancias Matem\u00e1ticas e de Computac \u00b8\u00e3o , University of S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038260547","display_name":"Anderson da Silva Soares","orcid":"https://orcid.org/0000-0002-2967-6077","observed_orcids":["https://orcid.org/0000-0002-2967-6077"]},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Soares, Anderson","raw_affiliation_strings":["Federal University of Goias , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Goias , Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057639095","display_name":"Frederico Santos de Oliveira","orcid":"https://orcid.org/0000-0002-5885-6747","observed_orcids":["https://orcid.org/0000-0002-5885-6747"]},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"de Oliveira, Frederico Santos","raw_affiliation_strings":["Federal University of Goias , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Goias , Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116386957","display_name":"Lucas Ferro Antunes de Oliveira","orcid":"https://orcid.org/0000-0003-4052-7993","observed_orcids":["https://orcid.org/0000-0003-4052-7993"]},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Oliveira, Lucas","raw_affiliation_strings":["Federal University of Technology - Paran\u00e1 , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Technology - Paran\u00e1 , Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019025805","display_name":"Ricardo Corso Fernandes","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junior, Ricardo Corso Fernandes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027870914","display_name":"Daniel Peixoto Pinto da Silva","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"da Silva, Daniel Peixoto Pinto","raw_affiliation_strings":["Federal University of Technology - Paran\u00e1 , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Technology - Paran\u00e1 , Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012436801","display_name":"Fernando Gorgulho Fayet","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fayet, Fernando Gorgulho","raw_affiliation_strings":["Instituto de Ci\u00eancias Matem\u00e1ticas e de Computac \u00b8\u00e3o , University of S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancias Matem\u00e1ticas e de Computac \u00b8\u00e3o , University of S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074157708","display_name":"Bruno Baldissera Carlotto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Carlotto, Bruno Baldissera","raw_affiliation_strings":["Instituto de Ci\u00eancias Matem\u00e1ticas e de Computac \u00b8\u00e3o , University of S\u00e3o Paulo , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancias Matem\u00e1ticas e de Computac \u00b8\u00e3o , University of S\u00e3o Paulo , Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019858243","display_name":"Lucas Rafael Stefanel Gris","orcid":"https://orcid.org/0000-0002-2099-5004","observed_orcids":["https://orcid.org/0000-0002-2099-5004"]},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gris, Lucas Rafael Stefanel","raw_affiliation_strings":["Federal University of Technology - Paran\u00e1 , Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Technology - Paran\u00e1 , Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059202822","display_name":"Sandra Maria Alu\u00edsio","orcid":"https://orcid.org/0000-0001-5108-2630","observed_orcids":["https://orcid.org/0000-0001-5108-2630"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alu\u00edsio, Sandra Maria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.7200000286102295},{"id":"https://openalex.org/keywords/spontaneous-speech","display_name":"spontaneous speech","score":0.6729999780654907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.47200000286102295},{"id":"https://openalex.org/keywords/european-portuguese","display_name":"European Portuguese","score":0.8299999833106995},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.9039999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421057224273682},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7331147789955139},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.697289764881134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6711500883102417},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6471684575080872},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.6109921336174011},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5901191830635071},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5742884278297424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5659477710723877},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5289974808692932},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4761474132537842},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.4755544364452362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41658711433410645},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13736769556999207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07246693968772888},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2110.15731","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15731","pdf_url":"https://arxiv.org/pdf/2110.15731","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,"listed_in":[],"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":"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":null,"raw_type":"text"},{"id":"mag:3209109064","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2110.15731.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2110.15731","doi":"https://doi.org/10.48550/arxiv.2110.15731","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.15731","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.15731","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15731","pdf_url":"https://arxiv.org/pdf/2110.15731","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,"listed_in":[],"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":"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1207375514","display_name":null,"funder_award_id":"Code 001","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G29316538","display_name":null,"funder_award_id":"(Code 001)","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G295657101","display_name":null,"funder_award_id":"2019/","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G3205371473","display_name":null,"funder_award_id":"C4AI-USP","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G4434403849","display_name":null,"funder_award_id":"308808/2020-7","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G497127911","display_name":"Center for Artificial Intelligence","funder_award_id":"19/07665-4","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G5658673143","display_name":null,"funder_award_id":"2019/07665-4","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G6674923580","display_name":null,"funder_award_id":"2019/07665-4","funder_id":"https://openalex.org/F4320307762","funder_display_name":"International Business Machines Corporation"},{"id":"https://openalex.org/G831127782","display_name":null,"funder_award_id":"#2019/07665-4","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G871200192","display_name":null,"funder_award_id":"Code 001","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320323204","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Goi\u00e1s","ror":"https://ror.org/00w8cq239"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3209109064.pdf","grobid_xml":"https://content.openalex.org/works/W3209109064.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1533314835","https://openalex.org/W2009041782","https://openalex.org/W2139851371","https://openalex.org/W2164777277","https://openalex.org/W2251171292","https://openalex.org/W2338317587","https://openalex.org/W2584286976","https://openalex.org/W2750497738","https://openalex.org/W2755294594","https://openalex.org/W2799441795","https://openalex.org/W2799473636","https://openalex.org/W2908510526","https://openalex.org/W2943058813","https://openalex.org/W2966095117","https://openalex.org/W2983040767","https://openalex.org/W2995929068","https://openalex.org/W3004753145","https://openalex.org/W3043665049","https://openalex.org/W3081670364","https://openalex.org/W3095410713","https://openalex.org/W3099782249","https://openalex.org/W3120114695","https://openalex.org/W3127012371","https://openalex.org/W3186550062","https://openalex.org/W3198878148","https://openalex.org/W6893675597"],"related_works":["https://openalex.org/W4309647876","https://openalex.org/W4406940750","https://openalex.org/W3186550062","https://openalex.org/W3081670364","https://openalex.org/W4308599760","https://openalex.org/W7155092639","https://openalex.org/W3126408801","https://openalex.org/W7162577775","https://openalex.org/W1517076465","https://openalex.org/W7097989724"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"recognition":[2],"(ASR)":[3],"is":[4,75],"a":[5,76,102,125,141],"complex":[6],"and":[7,71,134,151,167,171,191],"challenging":[8],"task.":[9],"In":[10,21],"recent":[11],"years,":[12],"there":[13,29],"have":[14],"been":[15],"significant":[16],"advances":[17],"in":[18,51,86,108,184],"the":[19,24,40,46,160,204,212],"area.":[20],"particular,":[22],"for":[23,36,106,169,201],"Brazilian":[25],"Portuguese":[26,118],"(BP)":[27],"language,":[28],"were":[30,177],"about":[31],"376":[32],"hours":[33],"public":[34,126],"available":[35,104,208],"ASR":[37,88,107,127,182,200],"task":[38],"until":[39],"second":[41],"half":[42],"of":[43,48,66,78,95,145],"2020.":[44],"With":[45],"release":[47],"new":[49],"datasets":[50,79],"early":[52],"2021,":[53],"this":[54],"number":[55],"increased":[56],"to":[57,179,195],"574":[58],"hours.":[59],"The":[60],"existing":[61],"resources,":[62],"however,":[63],"are":[64,84,206],"composed":[65],"audios":[67,119],"containing":[68,110],"only":[69],"read":[70],"prepared":[72],"speech.":[73],"There":[74],"lack":[77],"including":[80],"spontaneous":[81,189],"speech,":[82],"which":[83],"essential":[85],"different":[87],"applications.":[89],"This":[90],"paper":[91],"presents":[92],"CORAA":[93,114,148,170,175],"(Corpus":[94],"Annotated":[96],"Audios)":[97],"v1.":[98],"with":[99,186],"290.77":[100],"hours,":[101],"publicly":[103,207],"dataset":[105],"BP":[109,185],"validated":[111],"pairs":[112],"(audio-transcription).":[113],"also":[115,123],"contains":[116],"European":[117],"(4.69":[120],"hours).":[121],"We":[122],"present":[124],"model":[128,139],"based":[129],"on":[130,147,153,199],"Wav2Vec":[131],"2.0":[132],"XLSR-53":[133],"fine-tuned":[135],"over":[136],"CORAA.":[137],"Our":[138],"achieved":[140],"Word":[142],"Error":[143,162],"Rate":[144],"24.18%":[146],"test":[149,156],"set":[150],"20.08%":[152],"Common":[154,172],"Voice":[155],"set.":[157],"When":[158],"measuring":[159],"Character":[161],"Rate,":[163],"we":[164],"obtained":[165],"11.02%":[166],"6.34%":[168],"Voice,":[173],"respectively.":[174],"corpora":[176,205],"assembled":[178],"both":[180],"improve":[181],"models":[183],"phenomena":[187],"from":[188],"speech":[190],"motivate":[192],"young":[193],"researchers":[194],"start":[196],"their":[197],"studies":[198],"Portuguese.":[202],"All":[203],"at":[209],"https://github.com/nilc-nlp/CORAA":[210],"under":[211],"CC":[213],"BY-NC-ND":[214],"4.0":[215],"license.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2021-11-08T00:00:00"}
