{"id":"https://openalex.org/W2108251622","doi":"https://doi.org/10.3115/1219840.1219896","title":"Using conditional random fields for sentence boundary detection in speech","display_name":"Using conditional random fields for sentence boundary detection in speech","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2108251622","doi":"https://doi.org/10.3115/1219840.1219896","mag":"2108251622"},"language":"en","primary_location":{"id":"doi:10.3115/1219840.1219896","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1219840.1219896","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1219840.1219896","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics  - ACL '05","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1219840.1219896","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"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":true,"raw_author_name":"Yang Liu","raw_affiliation_strings":["ICSI, Berkeley","[ICSI, Berkeley]"],"affiliations":[{"raw_affiliation_string":"ICSI, Berkeley","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"[ICSI, Berkeley]","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","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":["SRI and ICSI","SRI and ICSI#TAB#"],"affiliations":[{"raw_affiliation_string":"SRI and ICSI","institution_ids":[]},{"raw_affiliation_string":"SRI and ICSI#TAB#","institution_ids":[]}]},{"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":["SRI and ICSI","SRI and ICSI#TAB#"],"affiliations":[{"raw_affiliation_string":"SRI and ICSI","institution_ids":[]},{"raw_affiliation_string":"SRI and ICSI#TAB#","institution_ids":[]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100355692"],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":8.6925,"has_fulltext":true,"cited_by_count":107,"citation_normalized_percentile":{"value":0.97660627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"451","last_page":"458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","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/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/computer-science","display_name":"Computer science","score":0.7952499985694885},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7797365188598633},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7748513221740723},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7092675566673279},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6491658091545105},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6015267968177795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5589593052864075},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.49381765723228455},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4933253824710846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47642001509666443},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46616655588150024},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43715158104896545},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.42284858226776123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952499985694885},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7797365188598633},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7748513221740723},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7092675566673279},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6491658091545105},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6015267968177795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5589593052864075},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.49381765723228455},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4933253824710846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47642001509666443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46616655588150024},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43715158104896545},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.42284858226776123},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1219840.1219896","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1219840.1219896","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1219840.1219896","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics  - ACL '05","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1219840.1219896","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1219840.1219896","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1219840.1219896","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics  - ACL '05","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G3898395754","display_name":"STIMULATE:  Modeling and Automatic Labeling of Hidden Word- Level Events in Spontaneous Speech","funder_award_id":"9619921","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8246102066","display_name":null,"funder_award_id":"MDA972-02-C-0038","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8299211410","display_name":"KDI: Cross-Modal Analysis of Signal and Sense: Multimedia Corpora and Computational Tools for Gesture, Speech, and Gaze Research","funder_award_id":"9980054","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309036","display_name":"Purdue University","ror":"https://ror.org/02dqehb95"},{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320323106","display_name":"Agricultural Research Development Agency","ror":"https://ror.org/01shbv660"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2108251622.pdf","grobid_xml":"https://content.openalex.org/works/W2108251622.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W26608090","https://openalex.org/W94670513","https://openalex.org/W171402391","https://openalex.org/W192736094","https://openalex.org/W1504308419","https://openalex.org/W1505342653","https://openalex.org/W1587490638","https://openalex.org/W1592796124","https://openalex.org/W2141099517","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2426479676","https://openalex.org/W2729906263","https://openalex.org/W4300987104"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2539884462"],"abstract_inverted_index":{"Sentence":[0],"boundary":[1,116],"detection":[2,117],"in":[3,119],"speech":[4,9,83,93],"is":[5,123],"important":[6],"for":[7,15,46,63,150],"enriching":[8],"recognition":[10,94],"output,":[11],"making":[12],"it":[13,122],"easier":[14],"humans":[16],"to":[17,22,72,125],"read":[18],"and":[19,34,42,66,84,92,109,148],"downstream":[20],"modules":[21],"process.":[23],"In":[24,50,96],"previous":[25],"work,":[26],"we":[27,53],"have":[28],"developed":[29],"hidden":[30],"Markov":[31],"model":[32,71,100,144],"(HMM)":[33],"maximum":[35],"entropy":[36],"(Maxent)":[37],"classifiers":[38],"that":[39,127],"integrate":[40],"textual":[41],"prosodic":[43],"knowledge":[44,153],"sources":[45],"detecting":[47],"sentence":[48,115],"boundaries.":[49],"this":[51,64,70],"paper,":[52],"evaluate":[54,77],"the":[55,107,113,128,137,152],"use":[56],"of":[57],"a":[58,102],"conditional":[59],"random":[60],"field":[61],"(CRF)":[62],"task":[65,118],"relate":[67],"results":[68,130],"with":[69],"our":[73,98],"prior":[74],"work.":[75],"We":[76],"across":[78],"two":[79],"corpora":[80],"(conversational":[81],"telephone":[82],"broadcast":[85],"news":[86],"speech)":[87],"on":[88,112],"both":[89],"human":[90],"transcriptions":[91],"output.":[95],"general,":[97],"CRF":[99],"yields":[101],"lower":[103],"error":[104],"rate":[105],"than":[106],"HMM":[108],"Maxent":[110],"models":[111],"NIST":[114],"speech,":[120],"although":[121],"interesting":[124],"note":[126],"best":[129],"are":[131],"achieved":[132],"by":[133],"three-way":[134],"voting":[135],"among":[136],"classifiers.":[138],"This":[139],"probably":[140],"occurs":[141],"because":[142],"each":[143],"has":[145],"different":[146],"strengths":[147],"weaknesses":[149],"modeling":[151],"sources.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":5}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}