{"id":"https://openalex.org/W3094871513","doi":"https://doi.org/10.1109/coginfocom50765.2020.9237817","title":"Improving Real-time Recognition of Morphologically Rich Speech with Transformer Language Model","display_name":"Improving Real-time Recognition of Morphologically Rich Speech with Transformer Language Model","publication_year":2020,"publication_date":"2020-09-23","ids":{"openalex":"https://openalex.org/W3094871513","doi":"https://doi.org/10.1109/coginfocom50765.2020.9237817","mag":"3094871513"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom50765.2020.9237817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom50765.2020.9237817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)","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/A5014608650","display_name":"Bal\u00e1zs Tarj\u00e1n","orcid":"https://orcid.org/0000-0002-9676-3082"},"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":true,"raw_author_name":"Balazs Tarjan","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary","SpeechTex Ltd., Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"SpeechTex Ltd., Budapest, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043901293","display_name":"Gy\u00f6rgy Szasz\u00e1k","orcid":null},"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":"Gyorgy Szaszak","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075146981","display_name":"Tibor Fegy\u00f3","orcid":null},"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":"Tibor Fegyo","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary","SpeechTex Ltd., Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"SpeechTex Ltd., Budapest, Hungary","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"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":"Peter Mihajlik","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary","THINKTech Research Center, V\u00e1c, Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"THINKTech Research Center, V\u00e1c, Hungary","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014608650"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55578769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"000491","last_page":"000496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.8453243970870972},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8046870231628418},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7979679107666016},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.642951488494873},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.6133331060409546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5752527117729187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5484548211097717},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5275059938430786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5028957724571228},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4836026728153229},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41970184445381165},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.1860346794128418},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09131690859794617},{"id":"https://openalex.org/keywords/comprehension-approach","display_name":"Comprehension approach","score":0.08266714215278625},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07358762621879578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453243970870972},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8046870231628418},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7979679107666016},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.642951488494873},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.6133331060409546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5752527117729187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5484548211097717},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5275059938430786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5028957724571228},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4836026728153229},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41970184445381165},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.1860346794128418},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09131690859794617},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.08266714215278625},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07358762621879578},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coginfocom50765.2020.9237817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom50765.2020.9237817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W309335912","https://openalex.org/W1425721496","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1971415293","https://openalex.org/W1979625042","https://openalex.org/W2037942319","https://openalex.org/W2042783153","https://openalex.org/W2110415041","https://openalex.org/W2117621558","https://openalex.org/W2121299803","https://openalex.org/W2140653524","https://openalex.org/W2158195707","https://openalex.org/W2295078202","https://openalex.org/W2402268235","https://openalex.org/W2532751415","https://openalex.org/W2714176837","https://openalex.org/W2888867175","https://openalex.org/W2939021222","https://openalex.org/W2943845043","https://openalex.org/W2962784628","https://openalex.org/W2964121744","https://openalex.org/W2970597249","https://openalex.org/W2972551035","https://openalex.org/W2980282514","https://openalex.org/W2990835715","https://openalex.org/W3024794924","https://openalex.org/W3025310782","https://openalex.org/W4239753979","https://openalex.org/W4255130329","https://openalex.org/W4293569503","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6661177966","https://openalex.org/W6739901393","https://openalex.org/W6763701032","https://openalex.org/W6777053822","https://openalex.org/W6836931785"],"related_works":["https://openalex.org/W4255155614","https://openalex.org/W2394860946","https://openalex.org/W761725120","https://openalex.org/W2009170886","https://openalex.org/W2071315630","https://openalex.org/W2897427480","https://openalex.org/W1508853749","https://openalex.org/W1745277","https://openalex.org/W2787311093","https://openalex.org/W2129812225"],"abstract_inverted_index":{"Transformer":[0,24,99],"models":[1,27,56],"have":[2],"become":[3],"to":[4,30,60,77],"state-of-the-art":[5],"in":[6,15,40,82,104],"natural":[7],"language":[8,13,26,55,100],"understanding,":[9],"their":[10,34,38],"use":[11],"for":[12,65,92],"modeling":[14],"Automatic":[16],"Speech":[17],"Recognition":[18],"(ASR)":[19],"is":[20],"also":[21,48],"promising.":[22],"Albeit":[23],"based":[25,111],"were":[28],"shown":[29,49],"improve":[31],"ASR":[32,120],"performance,":[33],"computational":[35],"complexity":[36],"makes":[37],"application":[39],"real-time":[41,66],"systems":[42],"quite":[43],"challenging.":[44],"It":[45],"has":[46],"been":[47],"that":[50,119],"the":[51,71,106,128],"knowledge":[52],"of":[53,73],"such":[54],"can":[57,122],"be":[58,123],"transferred":[59],"traditional":[61],"n-gram":[62],"models,":[63],"suitable":[64],"decoding.":[67],"This":[68],"paper":[69],"investigates":[70],"adaptation":[72],"this":[74],"transfer":[75],"approach":[76],"morphologically":[78],"rich":[79],"languages,":[80],"and":[81,131],"a":[83,89,98,113],"real":[84],"time":[85],"scenario.":[86],"We":[87,117],"propose":[88],"new":[90],"method":[91],"subword-based":[93],"neural":[94],"text":[95],"augmentation":[96],"with":[97],"model,":[101],"which":[102],"consists":[103],"retokenizing":[105],"training":[107],"corpus":[108],"into":[109],"subwords,":[110],"on":[112],"statistical":[114],"data-driven":[115],"approach.":[116],"demonstrate":[118],"performance":[121],"augmented":[124],"by":[125],"yet":[126],"reducing":[127],"vocabulary":[129],"size":[130],"alleviating":[132],"memory":[133],"consumption.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}