{"id":"https://openalex.org/W4387942868","doi":"https://doi.org/10.14209/sbrt.2023.1570916069","title":"Bilingual ASR model with language identification for Brazilian Portuguese and South-American Spanish","display_name":"Bilingual ASR model with language identification for Brazilian Portuguese and South-American Spanish","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387942868","doi":"https://doi.org/10.14209/sbrt.2023.1570916069"},"language":"en","primary_location":{"id":"doi:10.14209/sbrt.2023.1570916069","doi":"https://doi.org/10.14209/sbrt.2023.1570916069","is_oa":true,"landing_page_url":"http://dx.doi.org/10.14209/sbrt.2023.1570916069","pdf_url":"https://biblioteca.sbrt.org.br/articlefile/4446.pdf","source":{"id":"https://openalex.org/S4306501723","display_name":"Anais de XXXV Simp\u00f3sio Brasileiro de Telecomunica\u00e7\u00f5es e Processamento de Sinais","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Anais do XLI Simp\u00f3sio Brasileiro de Telecomunica\u00e7\u00f5es e Processamento de Sinais","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://biblioteca.sbrt.org.br/articlefile/4446.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033050828","display_name":"Felipe Farias","orcid":"https://orcid.org/0000-0001-7411-5562","observed_orcids":["https://orcid.org/0000-0001-7411-5562"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felipe Farias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081867747","display_name":"William Alberto Cruz Casta\u00f1eda","orcid":"https://orcid.org/0000-0002-9803-1387","observed_orcids":["https://orcid.org/0000-0002-9803-1387"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Alberto Cruz Casta\u00f1eda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064454384","display_name":"Wilmer Lobato","orcid":"https://orcid.org/0000-0002-3929-1218","observed_orcids":["https://orcid.org/0000-0002-3929-1218"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wilmer Lobato","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058612982","display_name":"Marcellus Amadeus","orcid":"https://orcid.org/0009-0002-7777-2562","observed_orcids":["https://orcid.org/0009-0002-7777-2562"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcellus Amadeus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1105,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26502952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"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/bilingual-speech-recognition","display_name":"bilingual speech recognition","score":0.8199999928474426},{"id":"https://openalex.org/keywords/language-identification","display_name":"language identification","score":0.9470000267028809},{"id":"https://openalex.org/keywords/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.9490000009536743},{"id":"https://openalex.org/keywords/latin-american-spanish","display_name":"Latin American Spanish","score":0.796999990940094},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.7739999890327454},{"id":"https://openalex.org/keywords/low-resource-speech-recognition","display_name":"low-resource speech recognition","score":0.7319999933242798},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.6830000281333923},{"id":"https://openalex.org/keywords/joint-encoders","display_name":"joint encoders","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7745252847671509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869089007377625},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.6805011630058289},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6435920000076294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5769777894020081},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5637155175209045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303263068199158},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5260786414146423},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.42036813497543335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40009909868240356},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.19621407985687256},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14209/sbrt.2023.1570916069","doi":"https://doi.org/10.14209/sbrt.2023.1570916069","is_oa":true,"landing_page_url":"http://dx.doi.org/10.14209/sbrt.2023.1570916069","pdf_url":"https://biblioteca.sbrt.org.br/articlefile/4446.pdf","source":{"id":"https://openalex.org/S4306501723","display_name":"Anais de XXXV Simp\u00f3sio Brasileiro de Telecomunica\u00e7\u00f5es e Processamento de Sinais","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Anais do XLI Simp\u00f3sio Brasileiro de Telecomunica\u00e7\u00f5es e Processamento de Sinais","raw_type":"proceedings-article"},{"id":"doi:10.20944/preprints202210.0480.v1","doi":"https://doi.org/10.20944/preprints202210.0480.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202210.0480.v1","pdf_url":"https://www.preprints.org/manuscript/202210.0480/v1/download","source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.14209/sbrt.2023.1570916069","doi":"https://doi.org/10.14209/sbrt.2023.1570916069","is_oa":true,"landing_page_url":"http://dx.doi.org/10.14209/sbrt.2023.1570916069","pdf_url":"https://biblioteca.sbrt.org.br/articlefile/4446.pdf","source":{"id":"https://openalex.org/S4306501723","display_name":"Anais de XXXV Simp\u00f3sio Brasileiro de Telecomunica\u00e7\u00f5es e Processamento de Sinais","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Anais do XLI Simp\u00f3sio Brasileiro de Telecomunica\u00e7\u00f5es e Processamento de Sinais","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387942868.pdf","grobid_xml":"https://content.openalex.org/works/W4387942868.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W1526974435","https://openalex.org/W2091746061","https://openalex.org/W2139851371","https://openalex.org/W2154740140","https://openalex.org/W2315995013","https://openalex.org/W2316579313","https://openalex.org/W2805087519","https://openalex.org/W2888922844","https://openalex.org/W2894835365","https://openalex.org/W2988736778","https://openalex.org/W2992847832","https://openalex.org/W2995929068","https://openalex.org/W2997787503","https://openalex.org/W3028785944","https://openalex.org/W3031533975","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3040454670","https://openalex.org/W3042007685","https://openalex.org/W3095410713","https://openalex.org/W3106807794","https://openalex.org/W3144073776","https://openalex.org/W3180180466","https://openalex.org/W3198275944","https://openalex.org/W3213029956","https://openalex.org/W4221161148","https://openalex.org/W4287553982","https://openalex.org/W4311000453"],"related_works":["https://openalex.org/W3186550062","https://openalex.org/W7165006180","https://openalex.org/W3081670364","https://openalex.org/W4385988039","https://openalex.org/W4309647876","https://openalex.org/W6986800228","https://openalex.org/W4414271035","https://openalex.org/W4406031362","https://openalex.org/W4406940750","https://openalex.org/W3042007685"],"abstract_inverted_index":{"Creating":[0],"accurate":[1],"and":[2,26,33,42,50,71],"reliable":[3],"low-resource":[4],"automatic":[5],"speech":[6,37],"recognition":[7],"(ASR)":[8],"models":[9],"remains":[10],"challenging":[11],"due":[12],"to":[13,84],"limited":[14],"curated":[15],"data.This":[16],"work":[17],"proposes":[18],"a":[19,46,72,80],"bilingual":[20,81],"ASR":[21],"model":[22],"for":[23,68],"Brazilian":[24],"Portuguese":[25],"Latin-American":[27],"Spanish":[28],"implemented":[29],"with":[30,62],"the":[31,55,85],"Wav2Vec2.0architecture":[32],"trained":[34],"on":[35],"multiple":[36],"datasets.It":[38],"combines":[39],"Language":[40],"Identification":[41],"Speech":[43],"Recognition,":[44],"employing":[45],"joint":[47],"feature":[48],"encoder":[49],"task-specific":[51],"context":[52],"encoders.Evaluation":[53],"in":[54,79],"Multilingual":[56],"Librispeech":[57],"dataset":[58],"demonstrates":[59],"promising":[60],"results,":[61],"an":[63],"average":[64],"accuracy":[65],"of":[66,77],"75.98%":[67],"language":[69],"identification":[70],"competitive":[73],"Word":[74],"Error":[75],"Rate":[76],"30.45%":[78],"setting,":[82],"comparable":[83],"Whisper":[86],"model.":[87]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2023-10-26T00:00:00"}
