{"id":"https://openalex.org/W2123654563","doi":"https://doi.org/10.1109/icassp.2006.1660106","title":"Use of Vocal Source Features in Speaker Segmentation","display_name":"Use of Vocal Source Features in Speaker Segmentation","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2123654563","doi":"https://doi.org/10.1109/icassp.2006.1660106","mag":"2123654563"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5110217764","display_name":"W.N. Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"W.N. Chan","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","Dept. of Electron. Eng., Chinese Univ. of, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Chinese Univ. of, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","Dept. of Electron. Eng., Chinese Univ. of, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Chinese Univ. of, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078485183","display_name":"Nengheng Zheng","orcid":"https://orcid.org/0000-0002-4493-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nengheng Zheng","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","Dept. of Electron. Eng., Chinese Univ. of, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Chinese Univ. of, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026707467","display_name":"Hua Ouyang","orcid":"https://orcid.org/0009-0001-4259-5132"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hua Ouyang","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","Dept. of Electron. Eng., Chinese Univ. of, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Chinese Univ. of, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"657"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9955000281333923,"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":0.8130522966384888},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7953478097915649},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7346112132072449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322008013725281},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.666843056678772},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6379225254058838},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6286718845367432},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5708825588226318},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5123285055160522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4707185626029968},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.46500787138938904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3598805069923401}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8130522966384888},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7953478097915649},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7346112132072449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322008013725281},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.666843056678772},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6379225254058838},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6286718845367432},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5708825588226318},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5123285055160522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4707185626029968},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.46500787138938904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3598805069923401}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W86066796","https://openalex.org/W1482605500","https://openalex.org/W1583160164","https://openalex.org/W2044591814","https://openalex.org/W2118209063","https://openalex.org/W2156255174","https://openalex.org/W2620921085","https://openalex.org/W6738833779"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W4310979479","https://openalex.org/W2125642021","https://openalex.org/W2144208207","https://openalex.org/W2099333848"],"abstract_inverted_index":{"This":[0,63],"paper":[1],"addresses":[2],"the":[3,52,76,101],"problem":[4],"of":[5,28,37,61,75,110],"speaker":[6,23,35,77],"segmentation":[7,12,20,78,90],"in":[8,15,100],"telephone":[9],"conversation.":[10],"The":[11,107],"is":[13,41],"done":[14],"three":[16],"steps:":[17],"1)":[18],"preliminary":[19],"to":[21,33,66,83,115],"hypothesize":[22],"turning":[24],"points;":[25],"2)":[26],"clustering":[27],"segments;":[29],"and":[30],"3)":[31],"re-segmentation":[32],"determine":[34],"identity":[36],"each":[38],"segment.":[39],"It":[40],"found":[42],"that":[43],"vocal":[44,54,69,111],"source":[45,70,112],"related":[46,56],"features":[47,57,71,113],"are":[48,92],"more":[49],"speaker-discriminative":[50],"than":[51],"conventional":[53],"tract":[55],"for":[58],"small":[59],"amount":[60],"data.":[62,88],"motivates":[64],"us":[65],"thoughtfully":[67],"incorporate":[68],"into":[72],"early":[73],"stages":[74],"process,":[79],"where":[80],"decisions":[81],"have":[82],"be":[84],"made":[85],"with":[86],"limited":[87],"Speaker":[89,104],"experiments":[91],"carried":[93],"out":[94],"on":[95],"36":[96],"summed":[97],"channel":[98],"conversations":[99],"NIST":[102],"2004":[103],"Recognition":[105],"Evaluation.":[106],"proposed":[108],"use":[109],"leads":[114],"noticeable":[116],"performance":[117],"improvement":[118]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}