{"id":"https://openalex.org/W4416657282","doi":"https://doi.org/10.63317/47jcmqefap7z","title":"Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets","display_name":"Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4416657282","doi":"https://doi.org/10.63317/47jcmqefap7z"},"language":"en","primary_location":{"id":"doi:10.63317/47jcmqefap7z","doi":"https://doi.org/10.63317/47jcmqefap7z","is_oa":true,"landing_page_url":"https://doi.org/10.63317/47jcmqefap7z","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.121.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.121.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116341319","display_name":"M\u00e1t\u00e9 Gedeon","orcid":"https://orcid.org/0009-0005-1429-8279","observed_orcids":["https://orcid.org/0009-0005-1429-8279"]},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"M\u00e1t\u00e9 Gedeon","raw_affiliation_strings":["Department of Telecommunications and Artificial Intelligence ,","ELTE Research Centre for Linguistics , Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Artificial Intelligence ,","institution_ids":[]},{"raw_affiliation_string":"ELTE Research Centre for Linguistics , Hungary","institution_ids":["https://openalex.org/I106118109","https://openalex.org/I2802350943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120003993","display_name":"Piroska Zs\u00f3fia Barta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Piroska Zs\u00f3fia Barta","raw_affiliation_strings":["Department of Telecommunications and Artificial Intelligence ,","ELTE Research Centre for Linguistics , Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Artificial Intelligence ,","institution_ids":[]},{"raw_affiliation_string":"ELTE Research Centre for Linguistics , Hungary","institution_ids":["https://openalex.org/I106118109","https://openalex.org/I2802350943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773","observed_orcids":["https://orcid.org/0000-0001-7532-9773"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Mihajlik","raw_affiliation_strings":["Department of Telecommunications and Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Artificial Intelligence ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035565670","display_name":"Tekla Etelka Gr\u00e1czi","orcid":"https://orcid.org/0000-0003-3351-9661","observed_orcids":["https://orcid.org/0000-0003-3351-9661"]},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tekla Etelka Graczi","raw_affiliation_strings":["Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics , Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics , Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083883060","display_name":"Anna Koh\u00e1ri","orcid":"https://orcid.org/0000-0003-2500-0149","observed_orcids":["https://orcid.org/0000-0003-2500-0149"]},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Anna Koh\u00e1ri","raw_affiliation_strings":["Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics , Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics , Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070593335","display_name":"Katalin M\u00e1dy","orcid":"https://orcid.org/0000-0002-4968-7849","observed_orcids":["https://orcid.org/0000-0002-4968-7849"]},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Katalin M\u00e1dy","raw_affiliation_strings":["Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics , Hungary","SpeechTex Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics , Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"SpeechTex Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9672,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93296375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1562","last_page":"1570"},"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":9.999999747378752e-05,"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/conversational-speech","display_name":"conversational speech","score":0.7919999957084656},{"id":"https://openalex.org/keywords/spontaneous-speech","display_name":"spontaneous speech","score":0.9449999928474426},{"id":"https://openalex.org/keywords/dialogue-corpus","display_name":"dialogue corpus","score":0.5270000100135803},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9129999876022339},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8090000152587891},{"id":"https://openalex.org/keywords/speech-disfluency","display_name":"disfluency","score":0.6620000004768372},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.5640000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857000231742859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6413000226020813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6169000267982483},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5321999788284302},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45320001244544983},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/47jcmqefap7z","doi":"https://doi.org/10.63317/47jcmqefap7z","is_oa":true,"landing_page_url":"https://doi.org/10.63317/47jcmqefap7z","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.121.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.13529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.13529","pdf_url":"https://arxiv.org/pdf/2511.13529","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.13529","doi":"https://doi.org/10.48550/arxiv.2511.13529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.13529","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.63317/47jcmqefap7z","doi":"https://doi.org/10.63317/47jcmqefap7z","is_oa":true,"landing_page_url":"https://doi.org/10.63317/47jcmqefap7z","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.121.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326762","display_name":"Nemzeti Kutat\u00e1si Fejleszt\u00e9si \u00e9s Innov\u00e1ci\u00f3s Hivatal","ror":null},{"id":"https://openalex.org/F4320335908","display_name":"Nemzeti Kutat\u00e1si, Fejleszt\u00e9si \u00e9s Innovaci\u00f3s Alap","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416657282.pdf","grobid_xml":"https://content.openalex.org/works/W4416657282.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3167533889"],"related_works":["https://openalex.org/W4221142121","https://openalex.org/W7163063942","https://openalex.org/W775622597","https://openalex.org/W7131858140","https://openalex.org/W6906269415","https://openalex.org/W7128096008","https://openalex.org/W6887365277","https://openalex.org/W4413368328","https://openalex.org/W74502586","https://openalex.org/W4408355549"],"abstract_inverted_index":{"The":[0],"advancement":[1],"of":[2,48,60,74,149],"automatic":[3],"speech":[4,51,62,80,159,171],"recognition":[5],"(ASR)":[6],"has":[7],"been":[8],"largely":[9],"enhanced":[10],"by":[11],"extensive":[12],"datasets":[13,38,102,163],"in":[14,91,184],"high-resource":[15],"languages,":[16],"while":[17],"languages":[18],"such":[19],"as":[20,118,120],"Hungarian":[21,50,79,170],"remain":[22],"underrepresented":[23],"due":[24,153],"to":[25,154,168],"limited":[26],"spontaneous":[27,61,75,123,180],"and":[28,40,94,124,136,157,164,173,181],"conversational":[29,92,150,182],"corpora.To":[30],"address":[31],"this":[32],"gap,":[33],"we":[34,166],"introduce":[35],"two":[36],"new":[37],"-BEA-Large":[39],"BEA-Dialogue":[41],"-constructed":[42],"from":[43,63],"the":[44,49,109,146],"previously":[45],"unprocessed":[46],"portions":[47],"corpus":[52,81],"named":[53],"BEA.BEA-Large":[54],"extends":[55],"BEA-Base":[56],"with":[57,67,108],"255":[58],"hours":[59,73],"433":[64],"speakers,":[65],"enriched":[66],"detailed":[68],"segment-level":[69],"metadata.BEA-Dialogue,":[70],"comprising":[71],"85":[72],"conversations,":[76],"is":[77],"a":[78,175],"featuring":[82],"natural":[83],"dialogues":[84],"partitioned":[85],"into":[86],"speaker-independent":[87],"subsets,":[88],"supporting":[89],"research":[90],"ASR":[93,106],"speaker":[95],"diarization.We":[96],"establish":[97],"reproducible":[98],"baselines":[99],"on":[100,122,126],"these":[101,162],"using":[103],"publicly":[104],"available":[105],"models,":[107],"fine-tuned":[110],"Fast":[111],"Conformer":[112],"model":[113],"achieving":[114],"word":[115],"error":[116,132],"rates":[117,133],"low":[119],"14.18%":[121],"4.8%":[125],"repeated":[127],"speech.Diarization":[128],"experiments":[129],"yield":[130],"diarization":[131],"between":[134],"12.46%":[135],"17.40%,":[137],"providing":[138],"reference":[139],"points":[140],"for":[141,178],"future":[142],"improvements.The":[143],"results":[144],"highlight":[145],"persistent":[147],"difficulty":[148],"ASR,":[151],"particularly":[152],"disfluencies,":[155],"overlaps,":[156],"informal":[158],"patterns.By":[160],"releasing":[161],"baselines,":[165],"aim":[167],"advance":[169],"technology":[172],"offer":[174],"methodological":[176],"framework":[177],"developing":[179],"benchmarks":[183],"other":[185],"languages.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-11-19T00:00:00"}