{"id":"https://openalex.org/W2148671289","doi":"https://doi.org/10.1109/icassp.2003.1202327","title":"UBM-based real-time speaker segmentation for broadcasting news","display_name":"UBM-based real-time speaker segmentation for broadcasting news","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2148671289","doi":"https://doi.org/10.1109/icassp.2003.1202327","mag":"2148671289"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202327","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5102458633","display_name":"Tingyao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"TingYao Wu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110491600","display_name":"Lie Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lie Lu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451984","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-9457-9364"},"institutions":[{"id":"https://openalex.org/I12870472","display_name":"Birmingham City University","ror":"https://ror.org/00t67pt25","country_code":"GB","type":"education","lineage":["https://openalex.org/I12870472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["Birmingham City University, Birmingham, UK"],"affiliations":[{"raw_affiliation_string":"Birmingham City University, Birmingham, UK","institution_ids":["https://openalex.org/I12870472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397026","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-1991-119X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-Jiang Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102458633"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":5.0021,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96305798,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9972000122070312,"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/T11309","display_name":"Music and Audio Processing","score":0.9883999824523926,"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/computer-science","display_name":"Computer science","score":0.790020227432251},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7330855131149292},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7012715339660645},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6602519154548645},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5943123698234558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5904891490936279},{"id":"https://openalex.org/keywords/broadcasting","display_name":"Broadcasting (networking)","score":0.5676966905593872},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.54014652967453},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5332961082458496},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47921425104141235},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.47255298495292664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4629363417625427},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4228655993938446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790020227432251},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7330855131149292},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7012715339660645},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6602519154548645},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5943123698234558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5904891490936279},{"id":"https://openalex.org/C110157686","wikidata":"https://www.wikidata.org/wiki/Q922122","display_name":"Broadcasting (networking)","level":2,"score":0.5676966905593872},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.54014652967453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5332961082458496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47921425104141235},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.47255298495292664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629363417625427},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4228655993938446},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1202327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202327","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/e78283dc-9dbf-4d94-a144-3a5e7bd0106a","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/e78283dc-9dbf-4d94-a144-3a5e7bd0106a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wu, T Y, Lu, L, Chen, K & Zhang, H J 2003, UBM-based real-time speaker segmentation for broadcasting news. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings|ICASSP IEEE Int Conf Acoust Speech Signal Process Proc. vol. 2, IEEE, pp. 193-196, 2003 IEEE International Conference on Accoustics, Speech, and Signal Processing, Hong Kong, 1/07/03.","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W192559706","https://openalex.org/W2041823554","https://openalex.org/W2075662881","https://openalex.org/W2110215948","https://openalex.org/W2129244720","https://openalex.org/W6607848239"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,40,78,81,100,123],"problem":[4],"of":[5,33,80],"real-time":[6,111],"speaker":[7,23,88,104,119,125],"change":[8,89,126],"detection":[9],"in":[10,13,74],"broadcast":[11],"news,":[12],"which":[14,31,107],"no":[15],"prior":[16],"knowledge":[17],"on":[18,47,94],"speakers":[19],"is":[20,25,54,108,113],"assumed.":[21],"Our":[22],"segmentation":[24],"a":[26,43,95],"\"coarse":[27],"to":[28,56,76,115],"refine\"":[29],"process,":[30],"consists":[32],"two":[34],"stages:":[35],"pre-segmentation":[36,41],"and":[37,70,131],"refinement.":[38],"In":[39,99],"stage,":[42,102],"new":[44],"approach":[45,138],"based":[46,93],"Gaussian":[48],"mixture":[49],"model-universal":[50],"background":[51],"model":[52],"(GMM-UBM)":[53],"proposed":[55,114],"categorize":[57],"feature":[58,84],"vectors":[59],"into":[60],"three":[61],"sets,":[62],"i.e.":[63],"reliable":[64,82],"speaker-related":[65,68,72,83],"set,":[66,73],"doubtful":[67],"set":[69],"unreliable":[71],"order":[75],"enhance":[77],"effect":[79],"vectors.":[85],"Then":[86],"potential":[87,124],"boundaries":[90,127],"are":[91],"detected":[92],"novel":[96],"distance":[97],"measure.":[98],"refinement":[101],"incremental":[103],"adaptation":[105],"(ISA),":[106],"suitable":[109],"for":[110],"requirement,":[112],"obtain":[116],"considerably":[117],"precise":[118],"models":[120],"so":[121],"that":[122,136],"can":[128],"be":[129],"confirmed":[130],"refined.":[132],"Experimental":[133],"results":[134],"demonstrate":[135],"our":[137],"yields":[139],"satisfactory":[140],"performance.":[141]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}