{"id":"https://openalex.org/W1898164463","doi":"https://doi.org/10.15439/2015f386","title":"Comparison of Language Models Trained on Written Texts and Speech Transcripts in the Context of Automatic Speech Recognition","display_name":"Comparison of Language Models Trained on Written Texts and Speech Transcripts in the Context of Automatic Speech Recognition","publication_year":2015,"publication_date":"2015-10-11","ids":{"openalex":"https://openalex.org/W1898164463","doi":"https://doi.org/10.15439/2015f386","mag":"1898164463"},"language":"en","primary_location":{"id":"doi:10.15439/2015f386","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2015f386","pdf_url":"https://2024.fedcsis.org/proceedings/2015/pliks/386.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://2024.fedcsis.org/proceedings/2015/pliks/386.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044199615","display_name":"Sebastian Dziadzio","orcid":null},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Sebastian Dziadzio","raw_affiliation_strings":["AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063064194","display_name":"Aleksandra Nabo\u017cny","orcid":"https://orcid.org/0000-0001-9534-142X"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Aleksandra Nabo\u017cny","raw_affiliation_strings":["AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028262029","display_name":"Aleksander Smywi\u0144ski-Pohl","orcid":"https://orcid.org/0000-0001-6684-0748"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Aleksander Smywi\u0144ski-Pohl","raw_affiliation_strings":["AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland","institution_ids":["https://openalex.org/I686019"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066410445","display_name":"Bartosz Zi\u00f3\u0142ko","orcid":"https://orcid.org/0000-0001-5485-8879"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bartosz Zi\u00f3\u0142ko","raw_affiliation_strings":["AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Faculty of Computer Science, Electronics and Telecommunications, Krakow, Poland","institution_ids":["https://openalex.org/I686019"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5902,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62409054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"5","issue":null,"first_page":"193","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9966999888420105,"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":0.9787999987602234,"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":0.7925846576690674},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7205979824066162},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6716440916061401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6442310214042664},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5751529932022095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5650205612182617},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5406237840652466},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5166668891906738},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5110941529273987},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.4951707422733307},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4608364701271057},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31816235184669495},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.30884233117103577},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2145070731639862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07268303632736206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925846576690674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7205979824066162},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6716440916061401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6442310214042664},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5751529932022095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5650205612182617},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5406237840652466},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5166668891906738},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5110941529273987},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.4951707422733307},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4608364701271057},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31816235184669495},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30884233117103577},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2145070731639862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07268303632736206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.15439/2015f386","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2015f386","pdf_url":"https://2024.fedcsis.org/proceedings/2015/pliks/386.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:a0206092c3e0450885f007c55ba62e69","is_oa":false,"landing_page_url":"https://doaj.org/article/a0206092c3e0450885f007c55ba62e69","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 5, Pp 193-197 (2015)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2015f386","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2015f386","pdf_url":"https://2024.fedcsis.org/proceedings/2015/pliks/386.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G704003479","display_name":null,"funder_award_id":"LIDER/37/69/L-3/11/NCBR/2012","funder_id":"https://openalex.org/F4320335039","funder_display_name":"Narodowe Centrum Bada\u0144 i Rozwoju"}],"funders":[{"id":"https://openalex.org/F4320335039","display_name":"Narodowe Centrum Bada\u0144 i Rozwoju","ror":"https://ror.org/05pwfyy15"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1898164463.pdf","grobid_xml":"https://content.openalex.org/works/W1898164463.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W7542544","https://openalex.org/W172230311","https://openalex.org/W1566315437","https://openalex.org/W1772032423","https://openalex.org/W2075310404","https://openalex.org/W2093585241","https://openalex.org/W2095483064","https://openalex.org/W2142937603","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W6600312833","https://openalex.org/W6674010617","https://openalex.org/W6680532216","https://openalex.org/W6808361500"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2152945827","https://openalex.org/W2784059283","https://openalex.org/W2291624303","https://openalex.org/W2105439218"],"abstract_inverted_index":{"We":[0,43],"investigate":[1],"whether":[2],"language":[3,49],"models":[4,50],"used":[5,88],"in":[6,58,67],"automatic":[7],"speech":[8,15,41,53],"recognition":[9],"(ASR)":[10],"should":[11],"be":[12],"trained":[13,51,79],"on":[14,19,52,80],"transcripts":[16,54],"rather":[17],"than":[18],"written":[20,38,56],"texts.":[21],"By":[22],"calculating":[23],"log-likelihood":[24],"statistic":[25],"for":[26],"part-of-speech":[27],"(POS)":[28],"n-grams,":[29],"we":[30,87],"show":[31,61],"that":[32,62],"there":[33],"are":[34],"significant":[35],"differences":[36],"between":[37],"texts":[39,57],"and":[40,55,60,101],"transcripts.":[42],"also":[44],"test":[45],"the":[46,64,76,89,96],"performance":[47],"of":[48,95,99],"ASR":[59],"using":[63],"former":[65],"results":[66],"greater":[68],"word":[69],"error":[70],"reduction":[71],"rates":[72],"(WERR),":[73],"even":[74],"if":[75],"model":[77],"is":[78],"much":[81],"smaller":[82],"corpora.":[83],"For":[84],"our":[85],"experiments":[86],"manually":[90],"labeled":[91],"one":[92],"million":[93],"subcorpus":[94],"National":[97],"Corpus":[98],"Polish":[100],"an":[102],"HTK":[103],"acoustic":[104],"model.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
