{"id":"https://openalex.org/W2034181906","doi":"https://doi.org/10.1109/icassp.2010.5495078","title":"Speaker clustering using vector quantization and spectral clustering","display_name":"Speaker clustering using vector quantization and spectral clustering","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2034181906","doi":"https://doi.org/10.1109/icassp.2010.5495078","mag":"2034181906"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5109220146","display_name":"Ken-ichi Iso","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ken-ichi Iso","raw_affiliation_strings":["Japan Research, Yahoo Japan Corporation, Minato, Tokyo, Japan","Yahoo! JAPAN Research, Yahoo Japan Corporation, Midtown Tower, 9-7-1 Akasaka, Minato-ku, Tokyo 107-6211 Japan"],"affiliations":[{"raw_affiliation_string":"Japan Research, Yahoo Japan Corporation, Minato, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Yahoo! JAPAN Research, Yahoo Japan Corporation, Midtown Tower, 9-7-1 Akasaka, Minato-ku, Tokyo 107-6211 Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109220146"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6973,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90300201,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4986","last_page":"4989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7917172908782959},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.7122073769569397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6774954795837402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5609705448150635},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5395338535308838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.505695104598999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4967809319496155},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.4916120171546936},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.47494032979011536},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4612385928630829},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.41223642230033875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.350019246339798}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7917172908782959},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7122073769569397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6774954795837402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5609705448150635},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5395338535308838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.505695104598999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4967809319496155},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.4916120171546936},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.47494032979011536},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4612385928630829},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.41223642230033875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.350019246339798},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W1524222317","https://openalex.org/W2107617395","https://openalex.org/W2132914434","https://openalex.org/W2159591770","https://openalex.org/W2165874743","https://openalex.org/W3034729383","https://openalex.org/W6601947329","https://openalex.org/W6631445998","https://openalex.org/W6684578312","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W1539956819","https://openalex.org/W2885181216","https://openalex.org/W2902307923","https://openalex.org/W3209524672","https://openalex.org/W4231226332","https://openalex.org/W2883283761","https://openalex.org/W2031333634","https://openalex.org/W2953558418","https://openalex.org/W1989705029","https://openalex.org/W2003897165"],"abstract_inverted_index":{"We":[0,64],"present":[1],"a":[2,21,25,33,47,87],"speaker":[3,108],"clustering":[4,43,49,90],"method":[5,19,80,101],"for":[6],"conversational":[7],"speech":[8,22],"recordings":[9],"that":[10,98],"contain":[11],"short":[12],"utterances":[13],"from":[14],"multiple":[15],"speakers.":[16],"The":[17,42,95],"proposed":[18,79,100],"represents":[20],"segment":[23],"with":[24,51,71,81],"vector":[26],"of":[27,60],"VQ":[28],"code":[29],"frequencies":[30],"and":[31,112],"uses":[32],"cosine":[34],"between":[35],"two":[36],"vectors":[37],"as":[38],"their":[39],"similarity":[40,62],"measure.":[41],"is":[44],"performed":[45],"by":[46],"spectral":[48],"algorithm":[50],"cluster":[52],"number":[53],"estimation":[54],"based":[55,85],"on":[56,67,86],"an":[57],"eigen":[58],"structure":[59],"the":[61,78,82,99,104],"matrix.":[63],"conducted":[65],"experiments":[66],"five":[68],"test":[69],"sets":[70],"different":[72],"utterance":[73],"length":[74],"distributions":[75],"to":[76],"compare":[77],"conventional":[83,105],"approach":[84],"hierarchical":[88],"agglomerative":[89],"using":[91],"BIC":[92],"stopping":[93],"criterion.":[94],"results":[96],"show":[97],"significantly":[102],"outperforms":[103],"one":[106],"in":[107],"diarization":[109],"error":[110],"rate":[111],"purity":[113],"metrics.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}