{"id":"https://openalex.org/W2103580452","doi":"https://doi.org/10.1109/tasl.2010.2090144","title":"Speaker Clustering Using Decision Tree-Based Phone Cluster Models With Multi-Space Probability Distributions","display_name":"Speaker Clustering Using Decision Tree-Based Phone Cluster Models With Multi-Space Probability Distributions","publication_year":2010,"publication_date":"2010-11-09","ids":{"openalex":"https://openalex.org/W2103580452","doi":"https://doi.org/10.1109/tasl.2010.2090144","mag":"2103580452"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2090144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2090144","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5111785302","display_name":"Han-Ping Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Han-Ping Shen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan","Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049377418","display_name":"Jui\u2010Feng Yeh","orcid":"https://orcid.org/0000-0003-2798-1569"},"institutions":[{"id":"https://openalex.org/I183570559","display_name":"National Chiayi University","ror":"https://ror.org/04gknbs13","country_code":"TW","type":"education","lineage":["https://openalex.org/I183570559"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jui-Feng Yeh","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Chiayi University, Taiwan","Department of Computer Science and Information Engineering, National Chiayi University, Chiayi, TAIWAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Chiayi University, Taiwan","institution_ids":["https://openalex.org/I183570559"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Chiayi University, Chiayi, TAIWAN","institution_ids":["https://openalex.org/I183570559"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan","Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8646,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8799262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":"5","first_page":"1289","last_page":"1300"},"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8188542127609253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7181081771850586},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6460714340209961},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6424885392189026},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5989090800285339},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5866031050682068},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5698346495628357},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48316115140914917},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4653379023075104},{"id":"https://openalex.org/keywords/phone-call","display_name":"Phone call","score":0.4448539614677429},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4237730801105499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42113447189331055}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8188542127609253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7181081771850586},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6460714340209961},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6424885392189026},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5989090800285339},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5866031050682068},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5698346495628357},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48316115140914917},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4653379023075104},{"id":"https://openalex.org/C2994270382","wikidata":"https://www.wikidata.org/wiki/Q2296401","display_name":"Phone call","level":3,"score":0.4448539614677429},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4237730801105499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42113447189331055},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1109/tasl.2010.2090144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2090144","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W86660359","https://openalex.org/W184672293","https://openalex.org/W198801378","https://openalex.org/W215371639","https://openalex.org/W799630062","https://openalex.org/W1471937481","https://openalex.org/W1512429158","https://openalex.org/W1530770299","https://openalex.org/W1534614538","https://openalex.org/W1591300715","https://openalex.org/W1815845248","https://openalex.org/W1967477266","https://openalex.org/W1976523127","https://openalex.org/W1998474788","https://openalex.org/W2018642651","https://openalex.org/W2024600147","https://openalex.org/W2038086080","https://openalex.org/W2095892407","https://openalex.org/W2101864798","https://openalex.org/W2103161388","https://openalex.org/W2107825049","https://openalex.org/W2110136872","https://openalex.org/W2114851258","https://openalex.org/W2115333237","https://openalex.org/W2118313846","https://openalex.org/W2128484087","https://openalex.org/W2133598522","https://openalex.org/W2134124529","https://openalex.org/W2134483327","https://openalex.org/W2135625868","https://openalex.org/W2136752740","https://openalex.org/W2141656153","https://openalex.org/W2143187963","https://openalex.org/W2143555316","https://openalex.org/W2146871184","https://openalex.org/W2152615462","https://openalex.org/W2159104102","https://openalex.org/W2159591770","https://openalex.org/W2161939451","https://openalex.org/W2164512637","https://openalex.org/W2166980079","https://openalex.org/W2398758317","https://openalex.org/W2542676733","https://openalex.org/W2544173146","https://openalex.org/W2552720424","https://openalex.org/W4248472876","https://openalex.org/W6608190014","https://openalex.org/W6630838124","https://openalex.org/W6635532411","https://openalex.org/W6638339531","https://openalex.org/W6642173193","https://openalex.org/W6676263640","https://openalex.org/W6729171785"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,158],"approach":[4],"to":[5,23,30,58,91,101,117,122,129],"speaker":[6,46,74,154,187],"clustering":[7,19,75,137,188],"using":[8],"decision":[9,49,99],"tree-based":[10],"phone":[11,18,27,105,125,144,163],"cluster":[12,28,106,126,145],"models":[13,29,121,127],"(DT-PCMs).":[14],"In":[15,73,156],"this":[16],"approach,":[17],"is":[20,40,89,114,139,166],"first":[21],"applied":[22,140],"construct":[24,102],"the":[25,48,93,97,103,119,123,130,135,176,180,190],"universal":[26],"accommodate":[31],"acoustic":[32],"characteristics":[33],"from":[34,96],"different":[35],"speakers.":[36],"Since":[37],"pitch":[38,61],"feature":[39],"highly":[41],"speaker-related":[42,94],"and":[43,62,67,81,183],"beneficial":[44],"for":[45,65,153,162,168,186],"identification,":[47],"trees":[50,100],"based":[51,76],"on":[52,77,141,189],"multi-space":[53],"probability":[54],"distributions":[55],"(MSDs),":[56],"useful":[57],"model":[59,164,169],"both":[60],"cepstral":[63],"features":[64,83],"voiced":[66],"unvoiced":[68],"speech":[69,87,132,151],"simultaneously,":[70],"are":[71],"constructed.":[72],"DT-PCMs,":[78],"contextual,":[79],"phonetic,":[80],"prosodic":[82],"of":[84],"each":[85,147],"input":[86,131,150],"segment":[88],"used":[90],"select":[92],"MSDs":[95],"MSD":[98],"initial":[104,120],"models.":[107],"The":[108],"maximum-likelihood":[109],"linear":[110],"regression":[111],"(MLLR)":[112],"method":[113,161],"then":[115],"employed":[116],"adapt":[118],"speaker-adapted":[124,143],"according":[128],"segment.":[133],"Finally,":[134],"agglomerative":[136],"algorithm":[138],"all":[142],"models,":[146],"representing":[148],"one":[149],"segment,":[152],"clustering.":[155],"addition,":[157],"efficient":[159],"estimation":[160],"merging":[165],"proposed":[167],"parameter":[170],"combination.":[171],"Experimental":[172],"results":[173],"show":[174],"that":[175],"MSD-based":[177],"DT-PCMs":[178],"outperform":[179],"conventional":[181],"GMM-":[182],"HMM-based":[184],"approaches":[185],"RT09":[191],"tasks.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}