{"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":null,"primary_location":{"id":"doi:10.63317/47jcmqefap7z","is_oa":false,"landing_page_url":"https://doi.org/10.63317/47jcmqefap7z","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.13529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116341319","display_name":"M\u00e1t\u00e9 Gedeon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00e1t\u00e9 Gedeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120003993","display_name":"Piroska Zs\u00f3fia Barta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piroska Zs\u00f3fia Barta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Mihajlik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035565670","display_name":"Tekla Etelka Gr\u00e1czi","orcid":"https://orcid.org/0000-0003-3351-9661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tekla Etelka Graczi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083883060","display_name":"Anna Koh\u00e1ri","orcid":"https://orcid.org/0000-0003-2500-0149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna Koh\u00e1ri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070593335","display_name":"Katalin M\u00e1dy","orcid":"https://orcid.org/0000-0002-4968-7849"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katalin M\u00e1dy","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02841599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.7268000245094299,"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":0.7268000245094299,"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":0.10980000346899033,"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":0.018799999728798866,"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/word","display_name":"Word (group theory)","score":0.5376999974250793},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5321999788284302},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4715000092983246},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.39430001378059387},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34779998660087585},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.3391000032424927}],"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","is_oa":false,"landing_page_url":"https://doi.org/10.63317/47jcmqefap7z","pdf_url":null,"source":null,"license":null,"license_id":null,"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","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,"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"},{"id":"doi: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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.13529","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,151],"advancement":[1],"of":[2,51,64,79,157],"automatic":[3],"speech":[4,54,66,85,167,180],"recognition":[5],"(ASR)":[6],"has":[7],"been":[8],"largely":[9],"enhanced":[10],"by":[11],"extensive":[12],"datasets":[13,39,108,172],"in":[14,96,193],"high-resource":[15],"languages,":[16],"while":[17],"languages":[18],"such":[19],"as":[20,124,126],"Hungarian":[21,53,84,179],"remain":[22],"underrepresented":[23],"due":[24,161],"to":[25,162,177],"limited":[26],"spontaneous":[27,65,80,129,189],"and":[28,42,99,130,143,165,173,182,190],"conversational":[29,97,158,191],"corpora.":[30],"To":[31],"address":[32],"this":[33],"gap,":[34],"we":[35,175],"introduce":[36],"two":[37],"new":[38],"--":[40,44],"BEA-Large":[41,58],"BEA-Dialogue":[43],"constructed":[45],"from":[46,67],"the":[47,52,115,154],"previously":[48],"unprocessed":[49],"portions":[50],"corpus":[55,86],"named":[56],"BEA.":[57],"extends":[59],"BEA-Base":[60],"with":[61,71,114],"255":[62],"hours":[63,78],"433":[68],"speakers,":[69],"enriched":[70],"detailed":[72],"segment-level":[73],"metadata.":[74],"BEA-Dialogue,":[75],"comprising":[76],"85":[77],"conversations,":[81],"is":[82],"a":[83,184],"featuring":[87],"natural":[88],"dialogues":[89],"partitioned":[90],"into":[91],"speaker-independent":[92],"subsets,":[93],"supporting":[94],"research":[95],"ASR":[98,112],"speaker":[100],"diarization.":[101],"We":[102],"establish":[103],"reproducible":[104],"baselines":[105],"on":[106,128,132],"these":[107,171],"using":[109],"publicly":[110],"available":[111],"models,":[113],"fine-tuned":[116],"Fast":[117],"Conformer":[118],"model":[119],"achieving":[120],"word":[121],"error":[122,139],"rates":[123,140],"low":[125],"14.18%":[127],"4.8%":[131],"repeated":[133],"speech.":[134],"Diarization":[135],"experiments":[136],"yield":[137],"diarization":[138],"between":[141],"12.46%":[142],"17.40%,":[144],"providing":[145],"reference":[146],"points":[147],"for":[148,187],"future":[149],"improvements.":[150],"results":[152],"highlight":[153],"persistent":[155],"difficulty":[156],"ASR,":[159],"particularly":[160],"disfluencies,":[163],"overlaps,":[164],"informal":[166],"patterns.":[168],"By":[169],"releasing":[170],"baselines,":[174],"aim":[176],"advance":[178],"technology":[181],"offer":[183],"methodological":[185],"framework":[186],"developing":[188],"benchmarks":[192],"other":[194],"languages.":[195]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-19T00:00:00"}