{"id":"https://openalex.org/W3208546935","doi":"https://doi.org/10.1109/sped53181.2021.9587345","title":"Establishing a Baseline of Romanian Speech-to-Text Models","display_name":"Establishing a Baseline of Romanian Speech-to-Text Models","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3208546935","doi":"https://doi.org/10.1109/sped53181.2021.9587345","mag":"3208546935"},"language":"en","primary_location":{"id":"doi:10.1109/sped53181.2021.9587345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5052276321","display_name":"Dan Ungureanu","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":"Dan Ungureanu","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025819568","display_name":"Madalina Badeanu","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":false,"raw_author_name":"Madalina Badeanu","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077701216","display_name":"Gabriela-Catalina Marica","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":false,"raw_author_name":"Gabriela-Catalina Marica","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072192995","display_name":"Mihai Dasc\u0103lu","orcid":"https://orcid.org/0000-0002-4815-9227"},"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":"Mihai Dascalu","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062940611","display_name":"Dan Tufi\u015f","orcid":"https://orcid.org/0000-0002-8280-9852"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan Ioan Tufis","raw_affiliation_strings":["Romanian Academy, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Romanian Academy, Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052276321"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78589426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.820906400680542},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7993220090866089},{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.7013200521469116},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5616562366485596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5437489748001099},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5399008393287659},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5228976607322693},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.49127525091171265},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4697718322277069},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4382728338241577},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42083901166915894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4086611270904541},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31894052028656006},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0913156270980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820906400680542},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7993220090866089},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.7013200521469116},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5616562366485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5437489748001099},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5399008393287659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5228976607322693},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.49127525091171265},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4697718322277069},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4382728338241577},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42083901166915894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4086611270904541},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31894052028656006},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0913156270980835},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped53181.2021.9587345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315989","display_name":"National Authority for Scientific Research and Innovation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1512805649","https://openalex.org/W1524333225","https://openalex.org/W1529912373","https://openalex.org/W1631260214","https://openalex.org/W1922655562","https://openalex.org/W2064675550","https://openalex.org/W2105594594","https://openalex.org/W2131342762","https://openalex.org/W2134800885","https://openalex.org/W2157331557","https://openalex.org/W2163925746","https://openalex.org/W2166637769","https://openalex.org/W2193413348","https://openalex.org/W2738884019","https://openalex.org/W2782451907","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2963341956","https://openalex.org/W2980286501","https://openalex.org/W2991356003","https://openalex.org/W3029923669","https://openalex.org/W3103005696","https://openalex.org/W3114757058","https://openalex.org/W3208065268","https://openalex.org/W6631362777","https://openalex.org/W6631505837","https://openalex.org/W6636811518","https://openalex.org/W6640090968","https://openalex.org/W6679855610","https://openalex.org/W6687566353","https://openalex.org/W6741399199","https://openalex.org/W6747836893","https://openalex.org/W6755207826","https://openalex.org/W6768798221","https://openalex.org/W6778259750","https://openalex.org/W6802419445"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2955724459","https://openalex.org/W2163537793","https://openalex.org/W2037769829","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W2402899696","https://openalex.org/W3021690593","https://openalex.org/W2992378684","https://openalex.org/W2125343999"],"abstract_inverted_index":{"With":[0],"the":[1,10,110,113,126,153,172],"increasing":[2],"usage":[3],"of":[4,27,34,54,96,105,112,139,169],"Natural":[5],"Language":[6],"Processing":[7],"to":[8,50,56,70,101],"facilitate":[9],"interactions":[11],"between":[12],"humans":[13],"and":[14,48,93,165],"machines,":[15],"automatic":[16],"speech":[17],"recognition":[18],"systems":[19],"have":[20],"become":[21],"increasingly":[22],"popular":[23],"as":[24],"a":[25,31,52,81,90,137,157,161,167],"result":[26],"their":[28],"utility":[29],"in":[30],"wide":[32],"range":[33],"applications.":[35],"In":[36],"this":[37],"paper":[38],"we":[39,134],"explore":[40],"well-known":[41],"open-source":[42],"speech-to-text":[43],"engines,":[44],"namely":[45],"CMUSphinx,":[46],"DeepSpeech,":[47],"Kaldi,":[49],"build":[51],"baseline":[53,83],"models":[55,69],"transcribe":[57],"Romanian":[58,87],"speech.":[59,106],"These":[60],"engines":[61],"employ":[62],"various":[63,97],"underlying":[64],"methods":[65],"from":[66,143],"hidden":[67],"Markov":[68],"deep":[71],"neural":[72],"networks":[73],"that":[74],"also":[75],"integrate":[76],"language":[77,92],"models,":[78],"thus":[79],"providing":[80],"solid":[82],"for":[84],"comparison.":[85],"Unfortunately,":[86],"is":[88,150],"still":[89],"low-resource":[91],"six":[94],"datasets":[95],"qualities":[98],"were":[99],"merged":[100],"obtain":[102],"104":[103],"hours":[104,141],"To":[107],"further":[108],"increase":[109],"size":[111],"gathered":[114],"corpora,":[115,133],"our":[116],"experiments":[117],"consider":[118],"data":[119],"augmentation":[120],"techniques,":[121],"specifically":[122],"SpecAugment,":[123],"applied":[124],"on":[125,171],"most":[127],"promising":[128],"model.":[129],"Besides":[130],"using":[131,152],"existing":[132],"publicly":[135],"release":[136],"dataset":[138],"11.5":[140],"generated":[142],"Governmental":[144],"transcripts.":[145],"The":[146],"best":[147],"performing":[148],"model":[149],"obtained":[151],"Kaldi":[154],"architecture,":[155],"considers":[156],"hybrid":[158],"structure":[159],"with":[160],"Deep":[162],"Neural":[163],"Network,":[164],"achieves":[166],"WER":[168],"3.10%":[170],"test":[173],"partition.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-28T23:10:37.245301","created_date":"2025-10-10T00:00:00"}
