{"id":"https://openalex.org/W2408228699","doi":"https://doi.org/10.21437/interspeech.2015-499","title":"Large scale speech-to-text translation with out-of-domain corpora using better context-based models and domain adaptation","display_name":"Large scale speech-to-text translation with out-of-domain corpora using better context-based models and domain adaptation","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2408228699","doi":"https://doi.org/10.21437/interspeech.2015-499","mag":"2408228699"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-499","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.isca-speech.org/archive/interspeech_2015/papers/i15_2272.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065193578","display_name":"Marcin Junczys-Dowmunt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128738","display_name":"Samsung (Poland)","ror":"https://ror.org/0381acm07","country_code":"PL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210128738"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Marcin Junczys-Dowmunt","raw_affiliation_strings":["Samsung Poland R&D Center, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Poland R&D Center, Warsaw, Poland","institution_ids":["https://openalex.org/I4210128738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076778841","display_name":"Pawe\u0142 Przybysz","orcid":"https://orcid.org/0000-0002-4883-0228"},"institutions":[{"id":"https://openalex.org/I4210128738","display_name":"Samsung (Poland)","ror":"https://ror.org/0381acm07","country_code":"PL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210128738"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Przybysz","raw_affiliation_strings":["Samsung Poland R&D Center, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Poland R&D Center, Warsaw, Poland","institution_ids":["https://openalex.org/I4210128738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010603951","display_name":"Arleta Staszuk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128738","display_name":"Samsung (Poland)","ror":"https://ror.org/0381acm07","country_code":"PL","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210128738"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Arleta Staszuk","raw_affiliation_strings":["Samsung Poland R&D Center, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Poland R&D Center, Warsaw, Poland","institution_ids":["https://openalex.org/I4210128738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103640991","display_name":"Eun-Kyoung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eun-Kyoung Kim","raw_affiliation_strings":["DMC R&D Center, Samsung Electronics, Suwon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DMC R&D Center, Samsung Electronics, Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329199","display_name":"Jaewon Lee","orcid":"https://orcid.org/0000-0002-4652-012X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewon Lee","raw_affiliation_strings":["DMC R&D Center, Samsung Electronics, Suwon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DMC R&D Center, Samsung Electronics, Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2107821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2272","last_page":"2276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9976000189781189,"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":0.8391931653022766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6509867906570435},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6474471688270569},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6251357793807983},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5868734121322632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5804070830345154},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5637401342391968},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5601983666419983},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5173375010490417},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4903264343738556},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.47895604372024536},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37966227531433105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391931653022766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6509867906570435},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6474471688270569},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6251357793807983},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5868734121322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5804070830345154},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5637401342391968},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5601983666419983},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5173375010490417},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4903264343738556},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.47895604372024536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37966227531433105},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-499","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/5af24b23-1e9f-4ab0-8db9-1847475db405","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/5af24b23-1e9f-4ab0-8db9-1847475db405","pdf_url":"http://www.isca-speech.org/archive/interspeech_2015/papers/i15_2272.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Junczys-Dowmunt, M, Przybysz, P, Staszuk, A, Kim, E-K & Lee, J 2015, Large Scale Speech-to-Text Translation with Out-of-Domain Corpora Using Better Context-Based Models and Domain Adaptation. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, Dresden, Germany, pp. 2272-2276, Interspeech 2015, Dresden, Germany, 6/09/15. < http://www.isca-speech.org/archive/interspeech_2015/papers/i15_2272.pdf >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/5af24b23-1e9f-4ab0-8db9-1847475db405","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/5af24b23-1e9f-4ab0-8db9-1847475db405","pdf_url":"http://www.isca-speech.org/archive/interspeech_2015/papers/i15_2272.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Junczys-Dowmunt, M, Przybysz, P, Staszuk, A, Kim, E-K & Lee, J 2015, Large Scale Speech-to-Text Translation with Out-of-Domain Corpora Using Better Context-Based Models and Domain Adaptation. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, Dresden, Germany, pp. 2272-2276, Interspeech 2015, Dresden, Germany, 6/09/15. < http://www.isca-speech.org/archive/interspeech_2015/papers/i15_2272.pdf >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2408228699.pdf","grobid_xml":"https://content.openalex.org/works/W2408228699.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W43226814","https://openalex.org/W132913264","https://openalex.org/W630532510","https://openalex.org/W1614298861","https://openalex.org/W1625582487","https://openalex.org/W1872443190","https://openalex.org/W2070150502","https://openalex.org/W2096783796","https://openalex.org/W2097927681","https://openalex.org/W2101105183","https://openalex.org/W2107440414","https://openalex.org/W2121227244","https://openalex.org/W2124807415","https://openalex.org/W2132445562","https://openalex.org/W2141440284","https://openalex.org/W2141766660","https://openalex.org/W2146574666","https://openalex.org/W2158195707","https://openalex.org/W2170716095","https://openalex.org/W2180952760","https://openalex.org/W2250653840","https://openalex.org/W2595715041","https://openalex.org/W2891920428","https://openalex.org/W2951166594"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W2383111961","https://openalex.org/W2756978580"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"described":[4],"the":[5,25,52,58,78,106,115,118],"process":[6],"of":[7,49,51,60,75,117],"building":[8],"a":[9,101],"large-scale":[10],"speech-to-text":[11],"pipeline.":[12],"Two":[13],"target":[14],"domains,":[15],"daily":[16],"conversations":[17,20],"and":[18,43,63,93,127,137,146],"travel-related":[19],"between":[21],"two":[22],"agents,":[23],"for":[24,124,143],"English-German":[26],"language":[27,91,97,128],"pair":[28],"(both":[29],"directions)":[30],"are":[31,141],"examined.":[32],"The":[33],"SMT":[34],"component":[35],"is":[36,110,122],"built":[37],"from":[38],"out-of-domain":[39,119],"but":[40],"freely-available":[41],"bilingual":[42],"monolingual":[44],"data.":[45],"We":[46],"make":[47],"use":[48],"most":[50],"known":[53],"available":[54],"resources":[55],"to":[56,100],"examine":[57],"effects":[59],"unrestricted":[61],"data":[62],"large":[64],"scale":[65],"models.":[66],"A":[67],"naive":[68],"baseline":[69,79],"delivers":[70],"solid":[71],"results":[72,140],"in":[73,133],"terms":[74],"MT-quality.":[76],"Extending":[77],"with":[80],"context-based":[81],"translation":[82,125],"model":[83],"features":[84],"like":[85],"operations":[86],"sequence":[87],"models,":[88,92],"higher-order":[89],"class-based":[90],"additional":[94],"web-scale":[95],"word-based":[96],"models":[98,126,129],"leads":[99],"system":[102],"that":[103],"significantly":[104],"outperforms":[105],"baseline.":[107],"Domain":[108],"adaption":[109],"performed":[111],"by":[112],"separately":[113],"weighting":[114],"influence":[116],"subcorpora.":[120],"This":[121],"explored":[123],"yielding":[130],"significant":[131],"improvements":[132],"both":[134],"cases.":[135],"Automatic":[136],"manual":[138],"evaluation":[139],"provided":[142],"raw":[144],"MT-quality":[145],"ASR+MT-quality.":[147]},"counts_by_year":[],"updated_date":"2026-09-01T08:31:24.195828","created_date":"2025-10-10T00:00:00"}