{"id":"https://openalex.org/W2407420912","doi":"https://doi.org/10.21437/interspeech.2015-260","title":"Improving speech recognition and keyword search for low resource languages using web data","display_name":"Improving speech recognition and keyword search for low resource languages using web data","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2407420912","doi":"https://doi.org/10.21437/interspeech.2015-260","mag":"2407420912"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-260","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-260","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://eprints.whiterose.ac.uk/152838/8/Mendels%20et%20al%202015%20Improving%20Speech%20Recognition%20and%20Keyword%20Search.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068567260","display_name":"Gideon Mendels","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gideon Mendels","raw_affiliation_strings":["Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109207771","display_name":"V\u00edctor Soto","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Soto","raw_affiliation_strings":["Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045037642","display_name":"Julia Hirschberg","orcid":"https://orcid.org/0000-0003-0689-7616"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Hirschberg","raw_affiliation_strings":["Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kate M. Knill","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024283093","display_name":"Anton Ragni","orcid":"https://orcid.org/0000-0003-0634-4456"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anton Ragni","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405764","display_name":"Haipeng Wang","orcid":"https://orcid.org/0009-0009-9392-8505"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haipeng Wang","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5068567260"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":12.0103,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98525386,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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":0.8465837240219116},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.665058434009552},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.599265992641449},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5806404948234558},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5423004031181335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49464723467826843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48776131868362427},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.47639957070350647},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4603528678417206},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4405973553657532},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11263230443000793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465837240219116},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.665058434009552},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.599265992641449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5806404948234558},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5423004031181335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49464723467826843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48776131868362427},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.47639957070350647},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4603528678417206},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4405973553657532},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11263230443000793},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-260","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-260","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:eprints.whiterose.ac.uk:152838","is_oa":true,"landing_page_url":null,"pdf_url":"http://eprints.whiterose.ac.uk/152838/8/Mendels%20et%20al%202015%20Improving%20Speech%20Recognition%20and%20Keyword%20Search.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:generic.eprints.org:755166","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/755166/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:eprints.whiterose.ac.uk:152838","is_oa":true,"landing_page_url":null,"pdf_url":"http://eprints.whiterose.ac.uk/152838/8/Mendels%20et%20al%202015%20Improving%20Speech%20Recognition%20and%20Keyword%20Search.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2407420912.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W161909597","https://openalex.org/W626798658","https://openalex.org/W630532510","https://openalex.org/W1506752962","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1733633583","https://openalex.org/W1975550806","https://openalex.org/W2005232502","https://openalex.org/W2028956843","https://openalex.org/W2040070072","https://openalex.org/W2042655742","https://openalex.org/W2080401855","https://openalex.org/W2094971681","https://openalex.org/W2096140469","https://openalex.org/W2105830342","https://openalex.org/W2117257534","https://openalex.org/W2121764873","https://openalex.org/W2136780519","https://openalex.org/W2155388323","https://openalex.org/W2164666834","https://openalex.org/W2277634955","https://openalex.org/W2398775317","https://openalex.org/W2759478409"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2370199378","https://openalex.org/W188567224","https://openalex.org/W1667554445","https://openalex.org/W2101955803","https://openalex.org/W1607797725","https://openalex.org/W2381145755","https://openalex.org/W4224255760","https://openalex.org/W2294172805","https://openalex.org/W2038770598"],"abstract_inverted_index":{"We":[0,26],"describe":[1],"the":[2,9,74,99,103],"use":[3],"of":[4,59,98,105],"text":[5,28],"data":[6,76],"scraped":[7],"from":[8,29,102],"web":[10,75],"to":[11],"augment":[12],"language":[13,44,57],"models":[14],"for":[15,22,56],"Automatic":[16],"Speech":[17],"Recognition":[18],"and":[19,39,50,63,86],"Keyword":[20,91],"Search":[21,92],"Low":[23],"Resource":[24],"Languages.":[25],"scrape":[27],"multiple":[30],"genres":[31],"including":[32],"blogs,":[33],"online":[34],"news,":[35],"translated":[36],"TED":[37],"talks,":[38],"subtitles.":[40],"Using":[41],"linearly":[42],"interpolated":[43],"models,":[45],"we":[46,71],"find":[47],"that":[48,73],"blogs":[49],"movie":[51],"subtitles":[52],"are":[53],"more":[54],"relevant":[55],"modeling":[58],"conversational":[60],"telephone":[61],"speech":[62],"obtain":[64],"large":[65],"reductions":[66],"in":[67,90],"out-of-vocabulary":[68,106],"keywords.":[69],"Furthermore,":[70],"show":[72],"can":[77],"improve":[78],"Term":[79],"Error":[80],"Rate":[81],"Performance":[82],"by":[83,93],"3.8%":[84],"absolute":[85,95],"Maximum":[87],"Term-Weighted":[88],"Value":[89],"0.0076-0.1059":[94],"points.":[96],"Much":[97],"gain":[100],"comes":[101],"reduction":[104],"items.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}