{"id":"https://openalex.org/W4297841455","doi":"https://doi.org/10.21437/interspeech.2022-10439","title":"Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech","display_name":"Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech","publication_year":2022,"publication_date":"2022-06-15","ids":{"openalex":"https://openalex.org/W4297841455","doi":"https://doi.org/10.21437/interspeech.2022-10439"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.07627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07627","pdf_url":"https://arxiv.org/pdf/2206.07627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},"type":"article","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.07627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085434299","display_name":"Jan Lehe\u010dka","orcid":"https://orcid.org/0000-0002-3889-8069"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lehe\u010dka, Jan","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072542443","display_name":"J\u00e1n \u0160vec","orcid":"https://orcid.org/0000-0001-8362-5927"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"\u0160vec, Jan","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010512605","display_name":"Ale\u0161 Pra\u017e\u00e1k","orcid":"https://orcid.org/0000-0001-9453-0034"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Pra\u017e\u00e1k, Ale\u0161","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057873612","display_name":"Josef Psutka","orcid":"https://orcid.org/0000-0003-4761-1645"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Psutka, Josef V.","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia Pilsen, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9422,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88202162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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":0.9980999827384949,"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":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9753999710083008,"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":0.9567000269889832,"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/czech","display_name":"Czech","score":0.9307750463485718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832835912704468},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6381216049194336},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6368356347084045},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5113984942436218},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3917599320411682},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3812706470489502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38088172674179077},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31888067722320557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10354134440422058},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08405131101608276},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0594734251499176},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.04628026485443115}],"concepts":[{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.9307750463485718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832835912704468},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6381216049194336},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6368356347084045},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5113984942436218},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3917599320411682},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3812706470489502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38088172674179077},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31888067722320557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10354134440422058},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08405131101608276},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0594734251499176},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.04628026485443115},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2206.07627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07627","pdf_url":"https://arxiv.org/pdf/2206.07627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.07627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07627","pdf_url":"https://arxiv.org/pdf/2206.07627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2127923419","https://openalex.org/W2134800885","https://openalex.org/W2979826702","https://openalex.org/W2981910996","https://openalex.org/W3015356564","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3119308075","https://openalex.org/W3197652246","https://openalex.org/W3198429080","https://openalex.org/W3200506395","https://openalex.org/W3207583491","https://openalex.org/W3207988762","https://openalex.org/W3213029956","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"our":[5],"progress":[6],"in":[7],"pretraining":[8],"Czech":[9],"monolingual":[10,84],"audio":[11],"transformers":[12],"from":[13,76],"a":[14,37,54],"large":[15,55,97],"dataset":[16,75],"containing":[17],"more":[18],"than":[19],"80":[20],"thousand":[21,45],"hours":[22,46],"of":[23,39,47,57,96],"unlabeled":[24,100],"speech,":[25],"and":[26,42,69,71,99,102],"subsequently":[27],"fine-tuning":[28,61],"the":[29,77,125],"model":[30],"on":[31,64],"automatic":[32],"speech":[33],"recognition":[34],"tasks":[35],"using":[36],"combination":[38],"in-domain":[40],"data":[41,121],"almost":[43],"6":[44],"out-of-domain":[48],"transcribed":[49],"speech.":[50],"We":[51],"are":[52,88,122],"presenting":[53],"palette":[56],"experiments":[58],"with":[59,105],"various":[60],"setups":[62],"evaluated":[63],"two":[65],"public":[66],"datasets":[67,101],"(CommonVoice":[68],"VoxPopuli)":[70],"one":[72],"extremely":[73],"challenging":[74],"MALACH":[78],"project.":[79],"Our":[80],"results":[81],"show":[82],"that":[83],"Wav2Vec":[85,110],"2.0":[86],"models":[87,111],"robust":[89],"ASR":[90,127],"systems,":[91],"which":[92],"can":[93],"take":[94],"advantage":[95],"labeled":[98],"successfully":[103],"compete":[104],"state-of-the-art":[106],"LVCSR":[107],"systems.":[108],"Moreover,":[109],"proved":[112],"to":[113],"be":[114],"good":[115],"zero-shot":[116],"learners":[117],"when":[118],"no":[119],"training":[120],"available":[123],"for":[124],"target":[126],"task.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-10-01T00:00:00"}
