{"id":"https://openalex.org/W2000223082","doi":"https://doi.org/10.1109/icassp.2010.5494999","title":"Automatic disfluency removal for improving spoken language translation","display_name":"Automatic disfluency removal for improving spoken language translation","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2000223082","doi":"https://doi.org/10.1109/icassp.2010.5494999","mag":"2000223082"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5494999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494873","display_name":"Jing Zheng","orcid":"https://orcid.org/0000-0003-2724-8471"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Zheng","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062598662","display_name":"Necip Faz\u0131l Ayan","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Necip Fazil Ayan","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"[Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100396375"],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":4.645,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94536079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5214","last_page":"5217"},"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9958999752998352,"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":0.8661878108978271},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6701167821884155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6271935701370239},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6237070560455322},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6081748604774475},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5776917338371277},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5488361716270447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.548678457736969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5269202589988708},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4384411871433258},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19913941621780396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8661878108978271},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6701167821884155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6271935701370239},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6237070560455322},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6081748604774475},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5776917338371277},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5488361716270447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.548678457736969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5269202589988708},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4384411871433258},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19913941621780396},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5494999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.385.6156","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.6156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/people/gokhan/pubs/ICASSP10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W52337014","https://openalex.org/W2088907244","https://openalex.org/W2101105183","https://openalex.org/W2149327368","https://openalex.org/W2153653739","https://openalex.org/W2161274063","https://openalex.org/W3202300147","https://openalex.org/W6681703963","https://openalex.org/W6802003531","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W4240926580","https://openalex.org/W2070920720","https://openalex.org/W2475062008","https://openalex.org/W2122294272","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2404510748","https://openalex.org/W3089218859"],"abstract_inverted_index":{"Statistical":[0],"machine":[1],"translation":[2],"(SMT)":[3],"systems":[4],"for":[5,42,71],"spoken":[6],"languages":[7],"suffer":[8],"from":[9,26],"conversational":[10,75],"speech":[11,18],"phenomena,":[12],"in":[13,88],"particular,":[14],"the":[15,22,44,49,56],"presence":[16],"of":[17,24,51,58],"disfluencies.":[19],"We":[20,47,68],"examine":[21],"impact":[23,57],"disfluencies":[25],"broadcast":[27,74],"conversation":[28],"data":[29],"on":[30,61],"our":[31,79],"hierarchical":[32],"phrase-based":[33],"SMT":[34,62],"system":[35],"and":[36,54,90],"implement":[37],"automatic":[38,80],"disfluency":[39,59,66,81],"removal":[40,60,82],"approaches":[41,53,83],"cleansing":[43],"MT":[45],"input.":[46],"evaluate":[48],"efficacy":[50],"proposed":[52],"investigate":[55],"performance":[63],"across":[64],"different":[65],"types.":[67],"show":[69],"that":[70],"translating":[72],"Mandarin":[73],"transcripts":[76],"into":[77],"English,":[78],"could":[84],"produce":[85],"significant":[86],"improvement":[87],"BLEU":[89],"TER.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}