{"id":"https://openalex.org/W2149205378","doi":"https://doi.org/10.1109/icassp.2006.1660168","title":"On Maximizing the Within-Cluster Homogeneity of Speaker Voice Characteristics For Speech Utterance Clustering","display_name":"On Maximizing the Within-Cluster Homogeneity of Speaker Voice Characteristics For Speech Utterance Clustering","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2149205378","doi":"https://doi.org/10.1109/icassp.2006.1660168","mag":"2149205378"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660168","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":"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/A5020303183","display_name":"Wei-Ho Tsai","orcid":"https://orcid.org/0000-0002-0867-7951"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Wei-Ho Tsai","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020303183"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":1.3972,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85568523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9948999881744385,"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":0.9927999973297119,"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/utterance","display_name":"Utterance","score":0.8416067361831665},{"id":"https://openalex.org/keywords/homogeneity","display_name":"Homogeneity (statistics)","score":0.7511630654335022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6846778392791748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6741411685943604},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6412187814712524},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5338469743728638},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4737551808357239},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4585951864719391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40094223618507385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3594133257865906},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23331394791603088},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1393601894378662}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8416067361831665},{"id":"https://openalex.org/C142259097","wikidata":"https://www.wikidata.org/wiki/Q5891314","display_name":"Homogeneity (statistics)","level":2,"score":0.7511630654335022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6846778392791748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6741411685943604},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6412187814712524},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5338469743728638},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4737551808357239},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4585951864719391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40094223618507385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3594133257865906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23331394791603088},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1393601894378662},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1660168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660168","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.9750","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.9750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iis.sinica.edu.tw/~whm/publish/papers/icassp06-speakerclustering.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W76945434","https://openalex.org/W1484181928","https://openalex.org/W1639032689","https://openalex.org/W2033403400","https://openalex.org/W2041823554","https://openalex.org/W2049633694","https://openalex.org/W2107617395","https://openalex.org/W2115415333","https://openalex.org/W2123838014","https://openalex.org/W2129244720","https://openalex.org/W2141262306","https://openalex.org/W2144130981","https://openalex.org/W2151299225","https://openalex.org/W2168175751","https://openalex.org/W2778716599","https://openalex.org/W2904250082","https://openalex.org/W4244030505","https://openalex.org/W6603105437","https://openalex.org/W6628802092","https://openalex.org/W6676027155"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2351687372","https://openalex.org/W2383414243","https://openalex.org/W2464407842","https://openalex.org/W2355273798"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,16,33,43,51,66,87,102],"problem":[4],"of":[5,20,50,105],"how":[6],"to":[7,100],"partition":[8],"unknown":[9],"speech":[10],"utterances":[11,44],"into":[12],"clusters,":[13],"such":[14],"that":[15,36,85],"overall":[17],"within-cluster":[18,28,52],"homogeneity":[19,29],"speakers'":[21],"voice":[22],"characteristics":[23],"can":[24],"be":[25,73],"maximized.":[26],"The":[27,95],"is":[30,56,81,97],"characterized":[31],"by":[32,59],"likelihood":[34,88],"probability":[35,55,89],"a":[37,46,61,91],"cluster":[38,68],"model,":[39],"trained":[40],"using":[41,60],"all":[42],"within":[45],"cluster,":[47],"matches":[48],"each":[49,70],"utterances.":[53],"Such":[54],"then":[57],"maximized":[58],"genetic":[62],"algorithm,":[63],"which":[64],"determines":[65],"best":[67],"where":[69],"utterance":[71],"should":[72],"located.":[74],"For":[75],"greater":[76],"computational":[77],"efficiency,":[78],"also":[79],"proposed":[80],"an":[82],"alternative":[83],"solution":[84],"approximates":[86],"with":[90],"divergence-based":[92],"model":[93],"similarity.":[94],"method":[96],"further":[98],"designed":[99],"estimate":[101],"optimal":[103],"number":[104],"clusters":[106],"automatically.":[107]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}