{"id":"https://openalex.org/W4416771694","doi":"https://doi.org/10.1109/sped67700.2025.11252367","title":"Open Source State-Of-the-Art Solution for Romanian Speech Recognition","display_name":"Open Source State-Of-the-Art Solution for Romanian Speech Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771694","doi":"https://doi.org/10.1109/sped67700.2025.11252367"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11252367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092639624","display_name":"Gabriel P\u00eerlogeanu","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Gabriel P\u00eerlogeanu","raw_affiliation_strings":["National University of Science and Technology Politehnica Bucharest,SpeeD,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology Politehnica Bucharest,SpeeD,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101877302","display_name":"Alexandru-Lucian Georgescu","orcid":"https://orcid.org/0000-0003-2122-4997"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Alexandru-Lucian Georgescu","raw_affiliation_strings":["National University of Science and Technology Politehnica Bucharest,SpeeD,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology Politehnica Bucharest,SpeeD,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032257745","display_name":"Horia Cucu","orcid":"https://orcid.org/0000-0002-8711-3854"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Horia Cucu","raw_affiliation_strings":["National University of Science and Technology Politehnica Bucharest,SpeeD,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology Politehnica Bucharest,SpeeD,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092639624"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.206122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9395999908447266,"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":0.9395999908447266,"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":0.04149999842047691,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.720300018787384},{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.6349999904632568},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5333999991416931},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5293999910354614},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5115000009536743},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.44519999623298645},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4334999918937683},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3476000130176544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709000110626221},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.720300018787384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.657800018787384},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5115000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4587000012397766},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11252367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2936774411","https://openalex.org/W2964172053","https://openalex.org/W2995181338","https://openalex.org/W3015190365","https://openalex.org/W3097777922","https://openalex.org/W3208546935","https://openalex.org/W3210397389","https://openalex.org/W4319862635","https://openalex.org/W4385575199","https://openalex.org/W4388692710","https://openalex.org/W4391021542","https://openalex.org/W4392902568","https://openalex.org/W4403172346"],"related_works":[],"abstract_inverted_index":{"In":[0,112],"this":[1],"work,":[2],"we":[3,63],"present":[4],"a":[5,34,49,65,78],"new":[6],"state-of-the-art":[7,86],"Romanian":[8,90],"Automatic":[9],"Speech":[10],"Recognition":[11],"(ASR)":[12],"system":[13,84],"based":[14],"on":[15,33],"NVIDIA\u2019s":[16],"FastConformer":[17],"architecture\u2014explored":[18],"here":[19],"for":[20,127],"the":[21,25],"first":[22],"time":[23],"in":[24,132],"context":[26],"of":[27,46,67],"Romanian.":[28],"We":[29],"train":[30],"our":[31,118],"model":[32],"large":[35],"corpus":[36],"of,":[37],"mostly,":[38],"weakly":[39],"supervised":[40],"transcriptions,":[41],"totaling":[42],"over":[43],"2,600":[44],"hours":[45],"speech.":[47],"Leveraging":[48],"hybrid":[50],"decoder":[51],"with":[52,77,99],"both":[53,128],"Connectionist":[54],"Temporal":[55],"Classification":[56],"(CTC)":[57],"and":[58,73,96,130],"Token-Duration":[59],"Transducer":[60],"(TDT)":[61],"branches,":[62],"evaluate":[64],"range":[66],"decoding":[68,122],"strategies":[69],"including":[70,93],"greedy,":[71],"ALSD,":[72],"CTC":[74],"beam":[75],"search":[76],"6-gram":[79],"token-level":[80],"language":[81],"model.":[82],"Our":[83],"achieves":[85],"performance":[87],"across":[88],"all":[89],"evaluation":[91],"benchmarks,":[92],"read,":[94],"spontaneous,":[95],"domain-specific":[97],"speech,":[98],"up":[100],"to":[101,108,114],"$27":[102],"\\%$":[103],"relative":[104],"WER":[105],"reduction":[106],"compared":[107],"previous":[109],"best-performing":[110],"systems.":[111],"addition":[113],"improved":[115],"transcription":[116],"accuracy,":[117],"approach":[119],"demonstrates":[120],"practical":[121],"efficiency,":[123],"making":[124],"it":[125],"suitable":[126],"research":[129],"deployment":[131],"low-latency":[133],"ASR":[134],"applications.":[135]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-27T00:00:00"}