{"id":"https://openalex.org/W158673570","doi":"https://doi.org/10.21437/interspeech.2005-851","title":"Comparing HMM, maximum entropy, and conditional random fields for disfluency detection","display_name":"Comparing HMM, maximum entropy, and conditional random fields for disfluency detection","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W158673570","doi":"https://doi.org/10.21437/interspeech.2005-851","mag":"158673570"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-851","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5100355884","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-4259-3882"},"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":"Yang Liu","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":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"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":"Andreas Stolcke","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/A5113657967","display_name":"Mary P. Harper","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Harper","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3313","last_page":"3316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T12031","display_name":"Speech and dialogue systems","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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.8933348655700684},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8612654209136963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830438017845154},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.6597753763198853},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6593160629272461},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6453585028648376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6218277812004089},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5947238802909851},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.4906252920627594},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4794536828994751},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47366127371788025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4699842035770416},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45215368270874023},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.32856500148773193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20898637175559998},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2036946415901184},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.18257218599319458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09333640336990356}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8933348655700684},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8612654209136963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830438017845154},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.6597753763198853},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6593160629272461},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6453585028648376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6218277812004089},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5947238802909851},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.4906252920627594},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4794536828994751},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47366127371788025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4699842035770416},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45215368270874023},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.32856500148773193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20898637175559998},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2036946415901184},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.18257218599319458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09333640336990356},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2005-851","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.218","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.218","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/eurospeech2005-df-detect.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.7100","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.7100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hlt.utdallas.edu/~yangl/papers/2005_Eurospeech-disfl.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"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":17,"referenced_works":["https://openalex.org/W26608090","https://openalex.org/W1488153692","https://openalex.org/W1556621813","https://openalex.org/W1577006985","https://openalex.org/W1846608861","https://openalex.org/W2021208044","https://openalex.org/W2065388812","https://openalex.org/W2088921122","https://openalex.org/W2098152775","https://openalex.org/W2099354200","https://openalex.org/W2100417418","https://openalex.org/W2147880316","https://openalex.org/W2163390156","https://openalex.org/W2165487751","https://openalex.org/W2169058332","https://openalex.org/W2405114413","https://openalex.org/W2426479676"],"related_works":["https://openalex.org/W2011251309","https://openalex.org/W2150969560","https://openalex.org/W65845428","https://openalex.org/W1945850644","https://openalex.org/W2344132714","https://openalex.org/W2385117199","https://openalex.org/W1993729825","https://openalex.org/W2536408262","https://openalex.org/W202303397","https://openalex.org/W2122520403"],"abstract_inverted_index":{"Automatic":[0],"detection":[1],"of":[2,82,89,106,132],"disfluencies":[3,51],"in":[4,52],"spoken":[5],"language":[6,20],"is":[7],"important":[8],"for":[9,17,49,103],"making":[10],"speech":[11,98],"recognition":[12,111,136],"output":[13],"more":[14,60],"readable,":[15],"and":[16,32,42,77,99,102,110,123,138],"aiding":[18],"downstream":[19],"processing":[21],"modules.":[22],"We":[23,86],"compare":[24],"a":[25,37,43,59],"generative":[26],"hidden":[27],"Markov":[28],"model":[29,41,64],"(HMM)-based":[30],"approach":[31,71],"two":[33,94,104],"conditional":[34,44,55,119],"models":[35,92],"\u2014":[36,48],"maximum":[38],"entropy":[39],"(Maxent)":[40],"random":[45],"field":[46],"(CRF)":[47],"detecting":[50],"speech.":[53],"The":[54],"modeling":[56,120],"approaches":[57,121],"provide":[58,125],"principled":[61],"way":[62],"to":[63],"correlated":[65],"features.":[66],"In":[67],"particular,":[68],"the":[69,74,80,118,128],"CRF":[70],"directly":[72],"detects":[73],"reparandum":[75],"regions,":[76],"thus":[78],"avoids":[79],"use":[81],"ad-hoc":[83],"heuristic":[84],"rules.":[85],"evaluate":[87],"performance":[88],"these":[90],"three":[91],"across":[93],"different":[95],"corpora":[96],"(conversational":[97],"broadcast":[100],"news)":[101],"types":[105],"transcriptions":[107,109],"(human":[108],"output).":[112],"Overall":[113],"we":[114],"find":[115],"that":[116,117],"(Maxent":[122],"CRF)":[124],"benefit":[126],"over":[127],"HMM":[129],"approach.":[130],"Effects":[131],"speaking":[133],"style,":[134],"word":[135],"errors,":[137],"future":[139],"directions":[140],"are":[141],"also":[142],"discussed.":[143],"1.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}