{"id":"https://openalex.org/W2106850183","doi":"https://doi.org/10.1109/icassp.2012.6288896","title":"Improving language models for ASR using translated in-domain data","display_name":"Improving language models for ASR using translated in-domain data","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2106850183","doi":"https://doi.org/10.1109/icassp.2012.6288896","mag":"2106850183"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052354286","display_name":"Stefan Kombrink","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Stefan Kombrink","raw_affiliation_strings":["Brno University of Technology, Czech Republic","Brno University of Technology, Czech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Czech","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020917394","display_name":"Tom\u00e1\u0161 Mikolov","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tomas Mikolov","raw_affiliation_strings":["Brno University of Technology, Czech Republic","Brno University of Technology, Czech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Czech","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Karafiat","raw_affiliation_strings":["Brno University of Technology, Czech Republic","Brno University of Technology, Czech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Czech","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Czech Republic","Brno University of Technology, Czech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology, Czech","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4405","last_page":"4408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9950000047683716,"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":0.8837733268737793},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.7081283926963806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.641538143157959},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6218452453613281},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5888242721557617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5848485231399536},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5792114734649658},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5695908069610596},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5650627613067627},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5506588220596313},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49765685200691223},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47184136509895325},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.47168830037117004},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4550342559814453},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42424774169921875},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4156762361526489},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10679468512535095},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10569855570793152},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10162734985351562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8837733268737793},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.7081283926963806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.641538143157959},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6218452453613281},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5888242721557617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5848485231399536},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5792114734649658},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5695908069610596},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5650627613067627},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5506588220596313},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49765685200691223},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47184136509895325},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.47168830037117004},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4550342559814453},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42424774169921875},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4156762361526489},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10679468512535095},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10569855570793152},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10162734985351562},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W191292882","https://openalex.org/W198385923","https://openalex.org/W2098618568","https://openalex.org/W2123798005","https://openalex.org/W2133267619","https://openalex.org/W2399127514"],"related_works":["https://openalex.org/W2463396630","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2114483840","https://openalex.org/W2010917994"],"abstract_inverted_index":{"Acquisition":[0],"of":[1,28,35],"in-domain":[2],"training":[3,60],"data":[4,61,76,89],"to":[5,31,43],"build":[6],"speech":[7,37,48],"recognition":[8,49],"systems":[9],"for":[10,96],"under-resourced":[11],"languages":[12],"can":[13],"be":[14],"a":[15,45,63],"costly,":[16],"time-demanding":[17],"and":[18,74,82,86,91],"tedious":[19],"process.":[20],"In":[21],"this":[22],"work,":[23],"we":[24],"propose":[25],"the":[26,66,97],"use":[27],"machine":[29],"translation":[30],"translate":[32],"English":[33],"transcripts":[34,53],"telephone":[36],"into":[38],"Czech":[39,46],"language":[40,58,68],"in":[41,62],"order":[42],"improve":[44],"CTS":[47],"system.":[50],"The":[51],"translated":[52],"are":[54],"used":[55],"as":[56],"additional":[57],"model":[59,69],"scenario":[64],"where":[65],"baseline":[67],"is":[70],"trained":[71],"on":[72,93],"off-":[73],"close-domain":[75],"only.":[77],"We":[78],"report":[79],"perplexities,":[80],"OOV":[81],"word":[83],"error":[84],"rates":[85],"examine":[87],"different":[88],"sets":[90],"translators":[92],"their":[94],"suitability":[95],"described":[98],"task.":[99]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
