{"id":"https://openalex.org/W68208136","doi":"https://doi.org/10.21437/icslp.2002-565","title":"Is the speaker done yet? faster and more accurate end-of-utterance detection using prosody","display_name":"Is the speaker done yet? faster and more accurate end-of-utterance detection using prosody","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W68208136","doi":"https://doi.org/10.21437/icslp.2002-565","mag":"68208136"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-565","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2061","last_page":"2064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9771999716758728,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8410799503326416},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8222246766090393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6885578036308289},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6440705060958862},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5309761762619019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.408196359872818},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3215232491493225}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8410799503326416},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8222246766090393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6885578036308289},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6440705060958862},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5309761762619019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.408196359872818},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3215232491493225}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2002-565","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.3589","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.3589","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/cgi-bin/run-distill?papers/icslp2002-endpointing.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1504308419","https://openalex.org/W1884359388","https://openalex.org/W1921634150","https://openalex.org/W1932883564","https://openalex.org/W2093555081","https://openalex.org/W2166184218","https://openalex.org/W2426479676"],"related_works":["https://openalex.org/W258725851","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W2140022733"],"abstract_inverted_index":{"We":[0,82,131],"examine":[1],"the":[2,14,59,67,73,80,122,139],"problem":[3],"of":[4,16,98,143],"end-of-utterance":[5],"(EOU)":[6],"detection":[7,23,90],"for":[8,31],"real-time":[9],"speech":[10],"recognition,":[11],"particularly":[12],"in":[13,53],"context":[15],"a":[17,27,54,85,118],"human-computer":[18],"dialog":[19],"system.":[20,60],"Current":[21],"EOU":[22,89,145],"algorithms":[24],"use":[25],"only":[26],"simple":[28],"pause":[29,49],"threshold":[30,74],"making":[32],"this":[33,134],"decision,":[34],"leading":[35],"to":[36,79,88,95,116],"two":[37],"problems.":[38,100],"First,":[39],"especially":[40],"as":[41],"speech-driven":[42],"interfaces":[43],"become":[44],"more":[45],"natural,":[46],"users":[47,63],"often":[48],"inside":[50],"utterances,":[51],"resulting":[52],"premature":[55],"cut":[56],"off":[57],"by":[58,105],"Second,":[61],"when":[62],"really":[64],"are":[65,103],"done,":[66],"minimum":[68],"system":[69],"wait":[70],"is":[71,128],"always":[72],"value,":[75],"needlessly":[76],"adding":[77],"time":[78],"interaction.":[81],"have":[83],"developed":[84],"new":[86],"approach":[87,135],"that":[91,120,124,133],"uses":[92],"prosodic":[93],"features":[94,102],"address":[96],"both":[97,138],"these":[99],"Prosodic":[101],"modeled":[104],"decision":[106],"trees":[107],"and":[108,141],"combined":[109],"with":[110],"an":[111,129],"event":[112],"N-gram":[113],"language":[114],"model":[115],"obtain":[117],"score":[119],"measures":[121],"likelihood":[123],"any":[125],"nonspeech":[126],"region":[127],"EOU.":[130],"find":[132],"dramatically":[136],"improves":[137],"accuracy":[140],"speed":[142],"online":[144],"detection.":[146],"1.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}