{"id":"https://openalex.org/W2148573886","doi":"https://doi.org/10.1109/icassp.2009.4960431","title":"Filtering web text to match target genres","display_name":"Filtering web text to match target genres","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2148573886","doi":"https://doi.org/10.1109/icassp.2009.4960431","mag":"2148573886"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5090536328","display_name":"M. A. Marin","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. A. Marin","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000339878","display_name":"Sergey Feldman","orcid":"https://orcid.org/0000-0003-0386-0922"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Feldman","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Ostendorf","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006404251","display_name":"Manisha Gupta","orcid":"https://orcid.org/0009-0005-9952-9987"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Gupta","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090536328"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":0.901,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81884298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":null,"first_page":"3705","last_page":"3708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.998199999332428,"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":0.9939000010490417,"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":0.8478018641471863},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6469907760620117},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6341037750244141},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6278591752052307},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5522753596305847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5408161282539368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.531604528427124},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.221889466047287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478018641471863},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6469907760620117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6341037750244141},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6278591752052307},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5522753596305847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408161282539368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.531604528427124},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.221889466047287},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.333.999","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.333.999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.washington.edu/research/guptalab/publications/FilteringWebTextICASSP2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W51407305","https://openalex.org/W79427365","https://openalex.org/W161909597","https://openalex.org/W1632114991","https://openalex.org/W1733633583","https://openalex.org/W1773803948","https://openalex.org/W1917042949","https://openalex.org/W2025157233","https://openalex.org/W2027582570","https://openalex.org/W2094971681","https://openalex.org/W2097560587","https://openalex.org/W2105830342","https://openalex.org/W2107682024","https://openalex.org/W2117257534","https://openalex.org/W2123938550","https://openalex.org/W2126414663","https://openalex.org/W2133486044","https://openalex.org/W2136780519","https://openalex.org/W2146888100","https://openalex.org/W2158195707","https://openalex.org/W2164666834","https://openalex.org/W2343954916","https://openalex.org/W2789080916","https://openalex.org/W2949696181","https://openalex.org/W6602125538","https://openalex.org/W6603324595","https://openalex.org/W6636649193","https://openalex.org/W6637497015","https://openalex.org/W6678485886","https://openalex.org/W6679817000"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2621258238","https://openalex.org/W2382781231","https://openalex.org/W4389443772","https://openalex.org/W2548721895","https://openalex.org/W2373456246","https://openalex.org/W2028097510","https://openalex.org/W2505877856","https://openalex.org/W3098003361","https://openalex.org/W2118730790"],"abstract_inverted_index":{"In":[0],"language":[1,68],"modeling":[2],"for":[3,53,60,64,70],"speech":[4],"recognition,":[5],"both":[6],"the":[7,13,16,20,23,26],"amount":[8],"of":[9,22,75],"training":[10],"data":[11],"and":[12,56],"match":[14],"to":[15,45,66],"target":[17],"task":[18],"impact":[19],"goodness":[21],"model,":[24],"with":[25],"trade-off":[27],"usually":[28],"favoring":[29],"more":[30],"data.":[31],"For":[32],"conversational":[33],"speech,":[34],"having":[35],"some":[36],"genre-matched":[37],"text":[38,63],"is":[39],"particularly":[40],"important,":[41],"but":[42],"also":[43],"hard":[44],"obtain.":[46],"This":[47],"paper":[48],"proposes":[49],"a":[50],"new":[51],"approach":[52],"genre":[54,65],"detection":[55],"compares":[57],"different":[58],"alternatives":[59],"filtering":[61],"Web":[62],"improve":[67],"models":[69],"use":[71],"in":[72],"automatic":[73],"transcription":[74],"broadcast":[76],"conversations":[77],"(talk":[78],"shows).":[79]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}