{"id":"https://openalex.org/W90695545","doi":"https://doi.org/10.21437/interspeech.2007-644","title":"Improving speech translation with automatic boundary prediction","display_name":"Improving speech translation with automatic boundary prediction","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W90695545","doi":"https://doi.org/10.21437/interspeech.2007-644","mag":"90695545"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-644","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-187219%22","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055441775","display_name":"Evgeny Matusov","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Evgeny Matusov","raw_affiliation_strings":["Lehrstuhl fuer Informatik 6, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl fuer Informatik 6, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091255196","display_name":"Dustin Hillard","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":"Dustin Hillard","raw_affiliation_strings":["Electrical Engineering, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathew Magimai-Doss","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-T\u00fcr","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"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":"Mari Ostendorf","raw_affiliation_strings":["Electrical Engineering, University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Lehrstuhl fuer Informatik 6, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl fuer Informatik 6, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055441775"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":6.7708,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96393504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2449","last_page":"2452"},"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":0.9998999834060669,"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":0.9975000023841858,"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":0.8309140205383301},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7340487837791443},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7244990468025208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6941910982131958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6698836088180542},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6627489328384399},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6422232389450073},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5965449213981628},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5874113440513611},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.5668218731880188},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5045510530471802},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4783463180065155},{"id":"https://openalex.org/keywords/language-translation","display_name":"Language translation","score":0.4722784459590912},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.44867751002311707},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.41484469175338745},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08447223901748657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06709551811218262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309140205383301},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7340487837791443},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7244990468025208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6941910982131958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6698836088180542},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6627489328384399},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6422232389450073},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5965449213981628},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5874113440513611},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.5668218731880188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5045510530471802},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4783463180065155},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.4722784459590912},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.44867751002311707},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.41484469175338745},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08447223901748657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06709551811218262},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2007-644","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:115608","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/115608","pdf_url":"http://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-187219%22","source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2007 : August 27 - 31, 2007, Antwerp, Belgium ; [proceedings of the 8th Annual Conference of the International Speech Communication Association and also the Tenth Biennial Eurospeech Conference]<br/>10. Biennial Eurospeech Conference, Antwerp, Belgium, 2007-08-27 - 2007-08-31","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.5260","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.5260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/319/Matusov--2007.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.7117","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.7117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ssli.ee.washington.edu/~hillard/matusov-mt-segmentation.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:126916","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/126916","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"8th annual conference of the International Speech Communication Association : Interspeech 2007 ; August 27 - 31, 2007, Antwerp, Belgium<br/>8. annual conference of the International Speech Communication Association, Antwerp, Belgium, 2007-08-27 - 2007-08-31","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:publications.rwth-aachen.de:115608","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/115608","pdf_url":"http://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-187219%22","source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2007 : August 27 - 31, 2007, Antwerp, Belgium ; [proceedings of the 8th Annual Conference of the International Speech Communication Association and also the Tenth Biennial Eurospeech Conference]<br/>10. Biennial Eurospeech Conference, Antwerp, Belgium, 2007-08-27 - 2007-08-31","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G3190074090","display_name":null,"funder_award_id":"HR0011-06-C-0023","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W90695545.pdf","grobid_xml":"https://content.openalex.org/works/W90695545.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W189129698","https://openalex.org/W596234542","https://openalex.org/W1484504603","https://openalex.org/W1631260214","https://openalex.org/W2053463056","https://openalex.org/W2099329894","https://openalex.org/W2101105183","https://openalex.org/W2146574666","https://openalex.org/W2149327368","https://openalex.org/W2158065314","https://openalex.org/W2398009384","https://openalex.org/W2426479676","https://openalex.org/W4233606598"],"related_works":["https://openalex.org/W2384400852","https://openalex.org/W3204898214","https://openalex.org/W2963259630","https://openalex.org/W4240926580","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2000013842","https://openalex.org/W4362495644","https://openalex.org/W2134714056"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,53,56,79,100,108,120],"influence":[4],"of":[5,17,55,99,119],"automatic":[6],"sentence":[7,29,38,124],"boundary":[8,39],"and":[9,24,31],"sub-sentence":[10],"punctuation":[11],"prediction":[12,49],"on":[13,89],"machine":[14],"translation":[15,58,105,109],"(MT)":[16],"automatically":[18,65],"recognized":[19],"speech.":[20],"We":[21,41,77,94],"use":[22],"prosodic":[23],"lexical":[25],"cues":[26],"to":[27,37,71,113],"determine":[28],"boundaries,":[30],"successfully":[32],"combine":[33],"two":[34,90],"complementary":[35],"approaches":[36],"prediction.":[40],"also":[42],"introduce":[43],"a":[44,83],"new":[45],"feature":[46],"for":[47,104,116],"segmentation":[48,101,117],"that":[50,96],"directly":[51,103],"considers":[52],"assumptions":[54],"phrase":[57],"model.":[59],"In":[60],"addition,":[61],"we":[62],"show":[63],"how":[64],"predicted":[66,121],"commas":[67],"can":[68],"be":[69],"used":[70],"constrain":[72],"reordering":[73],"in":[74,111],"MT":[75,87],"search.":[76],"evaluate":[78],"presented":[80],"methods":[81],"using":[82],"state-of-the-art":[84],"phrase-based":[85],"statistical":[86],"system":[88],"large":[91],"vocabulary":[92],"tasks.":[93],"find":[95],"careful":[97],"optimization":[98,115],"parameters":[102],"quality":[106,118],"improves":[107],"results":[110],"comparison":[112],"independent":[114],"source":[122],"language":[123],"boundaries.":[125],"1.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
