{"id":"https://openalex.org/W189129698","doi":"https://doi.org/10.21437/interspeech.2006-30","title":"The ICSI+ multilingual sentence segmentation system","display_name":"The ICSI+ multilingual sentence segmentation system","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W189129698","doi":"https://doi.org/10.21437/interspeech.2006-30","mag":"189129698"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058565083","display_name":"Molly E. Zimmerman","orcid":"https://orcid.org/0000-0002-8071-5369"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Zimmerman","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dilek Hakkani-T\u00fcr","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040611421","display_name":"James G. Fung","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Fung","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061251853","display_name":"Nikki Mirghafori","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Mirghafori","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006513718","display_name":"Luke Gottlieb","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Gottlieb","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"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":"Elizabeth Shriberg","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8854,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95910491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"paper 1808","last_page":"Mon1BuP.4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9993000030517578,"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":0.8414764404296875},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7081701755523682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6424385905265808},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6170662641525269},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5760406255722046},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5754230618476868},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5712500214576721},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5531265139579773},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5366140604019165},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5289506912231445},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4902036786079407},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4854593873023987},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.47464901208877563},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.43566960096359253},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09914600849151611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414764404296875},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7081701755523682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6424385905265808},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6170662641525269},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5760406255722046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5754230618476868},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5712500214576721},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5531265139579773},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5366140604019165},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5289506912231445},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4902036786079407},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4854593873023987},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.47464901208877563},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.43566960096359253},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09914600849151611},{"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:10.21437/interspeech.2006-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:ADA459046","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA459046","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","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":"DTIC","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W94670513","https://openalex.org/W171402391","https://openalex.org/W1504308419","https://openalex.org/W1504694836","https://openalex.org/W1526024327","https://openalex.org/W1530562053","https://openalex.org/W1539515721","https://openalex.org/W1608381367","https://openalex.org/W1934041838","https://openalex.org/W1985139039","https://openalex.org/W2053463056","https://openalex.org/W2096175520","https://openalex.org/W2097584131","https://openalex.org/W2111305191","https://openalex.org/W2113410090","https://openalex.org/W2129882154","https://openalex.org/W2146785422","https://openalex.org/W2426479676","https://openalex.org/W2441154163","https://openalex.org/W2463682495","https://openalex.org/W2915347754"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2990005675","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W2566359939","https://openalex.org/W2047632477"],"abstract_inverted_index":{"The":[0,104],"ICSI+":[1],"multilingual":[2],"sentence":[3],"segmentation":[4],"with":[5,115],"results":[6,106],"for":[7,37,47,128],"English":[8],"and":[9,24,41,44,56,67,81,95],"Mandarin":[10],"broadcast":[11],"news":[12],"automatic":[13],"speech":[14],"recognizer":[15],"transcriptions":[16],"represents":[17],"a":[18,75,116],"joint":[19],"effort":[20],"involving":[21],"ICSI,":[22],"SRI,":[23],"UT":[25],"Dallas.":[26],"Our":[27],"approach":[28],"is":[29,102],"based":[30],"on":[31],"using":[32],"hidden":[33,111],"event":[34,112],"language":[35,113],"models":[36,114],"exploiting":[38,48],"lexical":[39],"information,":[40],"maximum":[42],"entropy":[43],"boosting":[45],"classifiers":[46],"lexical,":[49],"as":[50,52],"well":[51],"prosodic,":[53],"speaker":[54],"change":[55],"syntactic":[57],"information.":[58],"We":[59],"demonstrate":[60],"that":[61,78,119],"the":[62,87,100],"proposed":[63],"methodology":[64,101],"including":[65],"pitch-":[66],"energy-related":[68],"prosodic":[69],"features":[70,84],"performs":[71],"significantly":[72],"better":[73],"than":[74],"baseline":[76],"system":[77],"uses":[79],"words":[80],"simple":[82],"pause":[83],"only.":[85],"Furthermore,":[86],"obtained":[88],"improvements":[89],"are":[90],"consistent":[91],"across":[92],"both":[93],"languages,":[94],"no":[96],"language-specific":[97],"adaptation":[98],"of":[99],"necessary.":[103],"best":[105],"were":[107],"achieved":[108],"by":[109],"combining":[110],"boosting-based":[117],"classifier":[118],"to":[120],"our":[121],"knowledge":[122],"has":[123],"not":[124],"previously":[125],"been":[126],"applied":[127],"this":[129],"task.":[130]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}