{"id":"https://openalex.org/W2044931612","doi":"https://doi.org/10.1109/coginfocom.2013.6719290","title":"Automatic phrase segmentation and clustering in spontaneous speech","display_name":"Automatic phrase segmentation and clustering in spontaneous speech","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2044931612","doi":"https://doi.org/10.1109/coginfocom.2013.6719290","mag":"2044931612"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom.2013.6719290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2013.6719290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 4th International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"},"type":"article","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/A5032873613","display_name":"Andr\u00e1s Beke","orcid":null},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Andras Beke","raw_affiliation_strings":["Research Institute of Linguistics, Hungarian Academy of Sciences","Res. Inst. of Linguistics, Hungary"],"affiliations":[{"raw_affiliation_string":"Research Institute of Linguistics, Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I7597260"]},{"raw_affiliation_string":"Res. Inst. of Linguistics, Hungary","institution_ids":["https://openalex.org/I2802350943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043901293","display_name":"Gy\u00f6rgy Szasz\u00e1k","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Gyorgy Szaszak","raw_affiliation_strings":["Dept. of Telecommunications and Media Informatics, Budapest University of Technology and Economics","Dept. of Telecommun. & Media Inf., Budapest Univ. of Technol. & Econ., Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Dept. of Telecommunications and Media Informatics, Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Dept. of Telecommun. & Media Inf., Budapest Univ. of Technol. & Econ., Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022860601","display_name":"Viola V\u00e1radi","orcid":"https://orcid.org/0000-0001-7984-1387"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Viola Varadi","raw_affiliation_strings":["Dept. of Phonetics, E\u00f6tv\u00f6s Lor\u00e1nd University","Dept. of Phonetics, Eotvos Lorand Univ., Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Dept. of Phonetics, E\u00f6tv\u00f6s Lor\u00e1nd University","institution_ids":["https://openalex.org/I106118109"]},{"raw_affiliation_string":"Dept. of Phonetics, Eotvos Lorand Univ., Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032873613"],"corresponding_institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":0.9888,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82533984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"459","last_page":"462"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9969000220298767,"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":0.7913222908973694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6922053098678589},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.6500241756439209},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6467528343200684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6344070434570312},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5627059936523438},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5483815670013428},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5107583999633789},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5103160738945007},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4969229996204376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49256545305252075},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43794816732406616},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.43118977546691895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3718041777610779},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.35474976897239685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913222908973694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6922053098678589},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.6500241756439209},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6467528343200684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6344070434570312},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5627059936523438},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5483815670013428},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5107583999633789},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5103160738945007},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4969229996204376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49256545305252075},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43794816732406616},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.43118977546691895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3718041777610779},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.35474976897239685},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/coginfocom.2013.6719290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2013.6719290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 4th International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"},{"id":"pmh:oai:real.mtak.hu:9059","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400081","display_name":"Repository of the Academy's Library (Library of the Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210140733","host_organization_name":"Library and Information Centre of the Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I4210140733"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W54137821","https://openalex.org/W1484181928","https://openalex.org/W1506716879","https://openalex.org/W1561466012","https://openalex.org/W1608101656","https://openalex.org/W1990448242","https://openalex.org/W2029520813","https://openalex.org/W2032751491","https://openalex.org/W2043513322","https://openalex.org/W2069059998","https://openalex.org/W2074817945","https://openalex.org/W2093414802","https://openalex.org/W2093961534","https://openalex.org/W2127218421","https://openalex.org/W2151251521","https://openalex.org/W2161807040","https://openalex.org/W4238946686","https://openalex.org/W4285719527","https://openalex.org/W6678914141"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W114226241"],"abstract_inverted_index":{"The":[0,37,50,130],"aim":[1],"of":[2,32,77],"this":[3],"research":[4],"is":[5,42,70,86],"to":[6,44,152],"segment":[7],"spontaneous":[8,35,39,51,146],"speech":[9,40,47,99],"using":[10],"an":[11,126],"unsupervised":[12],"learning":[13],"technique.":[14,106],"We":[15],"are":[16,53,94,112],"especially":[17],"interested":[18],"from":[19],"a":[20,46,82,104,149],"machine":[21],"perception":[22],"or":[23],"detection":[24,76],"point-of-view,":[25],"and":[26,60,79,103,121,140],"focus":[27],"on":[28,98,118],"revealing":[29],"some":[30],"structure":[31],"prosody":[33],"in":[34],"speech.":[36,154],"BEA":[38],"database":[41],"used":[43],"develop":[45],"segmentation":[48,84],"system.":[49],"narratives":[52],"annotated":[54],"manually":[55],"for":[56,63,143],"intonational":[57],"phrases":[58,65],"(IP)":[59],"further":[61],"divided":[62],"phonological":[64],"(PP).":[66],"Word":[67],"level":[68],"transcription":[69],"also":[71],"provided.":[72],"For":[73],"the":[74,89,92,108,115,134],"automatic":[75],"IPs":[78,93],"embedded":[80],"PPs,":[81],"two-step":[83],"method":[85,136],"applied.":[87],"In":[88,107],"first":[90],"step,":[91,110],"detected":[95],"automatically":[96],"based":[97,117],"energy,":[100],"spectral":[101],"centroid":[102],"double-thresholding":[105],"second":[109],"PPs":[111],"segmented":[113],"within":[114],"IPs,":[116],"F0,":[119],"energy":[120],"Kullback-Leibler":[122],"divergence":[123],"combined":[124],"with":[125,148],"adaptive":[127],"thresholding":[128],"method.":[129],"results":[131],"show":[132],"that":[133],"proposed":[135],"can":[137],"provide":[138],"good":[139],"efficient":[141],"framework":[142],"segmenting":[144],"Hungarian":[145],"speech,":[147],"performance":[150],"close":[151],"read":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}