{"id":"https://openalex.org/W99811769","doi":"https://doi.org/10.21437/icslp.2002-193","title":"Unsupervised speaker segmentation of telephone conversations","display_name":"Unsupervised speaker segmentation of telephone conversations","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W99811769","doi":"https://doi.org/10.21437/icslp.2002-193","mag":"99811769"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-193","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/A5025786251","display_name":"A. E. Rosenberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aaron E. Rosenberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051646883","display_name":"Allen L. Gorin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Allen Gorin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380643","display_name":"Zhu Liu","orcid":"https://orcid.org/0000-0003-4326-5335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103091951","display_name":"Srinivas Parthasarathy","orcid":"https://orcid.org/0000-0001-8928-9821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Parthasarathy","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":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"565","last_page":"568"},"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":0.9984999895095825,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7649781703948975},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7489423751831055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7313878536224365},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7313356399536133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6683348417282104},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.6672689914703369},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5782700181007385},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5582597255706787},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.5029625296592712},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46753713488578796},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41606035828590393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40423640608787537},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15125927329063416},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06530404090881348}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7649781703948975},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7489423751831055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313878536224365},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7313356399536133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6683348417282104},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.6672689914703369},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5782700181007385},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5582597255706787},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.5029625296592712},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46753713488578796},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41606035828590393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40423640608787537},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15125927329063416},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06530404090881348},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2002-193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-193","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3765491","https://openalex.org/W20023308","https://openalex.org/W1607155129","https://openalex.org/W1924751832","https://openalex.org/W1987663579","https://openalex.org/W2102453655","https://openalex.org/W2127914268","https://openalex.org/W2151299225","https://openalex.org/W2335060803"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"A":[0],"process":[1,19],"for":[2],"segmenting":[3],"2-speaker":[4],"telephone":[5],"conversations":[6],"by":[7],"speaker":[8,12],"with":[9,79],"no":[10],"prior":[11],"models":[13],"is":[14,70],"described":[15],"and":[16,28,33,39,87],"evaluated.":[17],"The":[18,41,55],"consists":[20],"of":[21,36,72,82,85],"an":[22],"initial":[23],"segmentation":[24],"using":[25],"acoustic":[26],"change":[27],"pause":[29],"detection,":[30],"segment":[31,37],"clustering,":[32],"iterative":[34],"modeling":[35],"clusters":[38],"resegmentation.":[40],"technique":[42,56],"has":[43],"been":[44],"evaluated":[45],"on":[46],"6,":[47],"approximately":[48],"3":[49],"min":[50],"long,":[51],"customer":[52],"care":[53],"conversations.":[54],"does":[57],"not":[58],"resolve":[59],"short":[60],"(":[61,76],"2":[62],"secs)":[63,78],"or":[64,91],"overlapping":[65],"segments":[66,75],"very":[67],"well,":[68],"but":[69],"capable":[71],"detecting":[73],"longer":[74],"4":[77],"miss":[80],"rates":[81,89],"the":[83],"order":[84],"10%":[86],"confusion":[88],"2%":[90],"less.":[92]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
