{"id":"https://openalex.org/W2162767715","doi":"https://doi.org/10.1109/iscslp.2010.5684888","title":"Multidimensional scaling for fast speaker clustering","display_name":"Multidimensional scaling for fast speaker clustering","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2162767715","doi":"https://doi.org/10.1109/iscslp.2010.5684888","mag":"2162767715"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language 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/A5112137296","display_name":"Chi-Chun Hsia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chi-Chun Hsia","raw_affiliation_strings":["ICT-Enabled Healthcare Program, Industrial Technology and Research Institute, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"ICT-Enabled Healthcare Program, Industrial Technology and Research Institute, Tainan, Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007724753","display_name":"Kuo\u2010Yuan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Yuan Lee","raw_affiliation_strings":["ICT-Enabled Healthcare Program, Industrial Technology and Research Institute, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"ICT-Enabled Healthcare Program, Industrial Technology and Research Institute, Tainan, Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110250605","display_name":"Chih-Chieh Chuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Chieh Chuang","raw_affiliation_strings":["ICT-Enabled Healthcare Program, Industrial Technology and Research Institute, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"ICT-Enabled Healthcare Program, Industrial Technology and Research Institute, Tainan, Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052495842","display_name":"Yu\u2010Hsien Chiu","orcid":"https://orcid.org/0000-0002-8233-4631"},"institutions":[{"id":"https://openalex.org/I152743029","display_name":"Kaohsiung Medical University","ror":"https://ror.org/03gk81f96","country_code":"TW","type":"education","lineage":["https://openalex.org/I152743029"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Hsien Chiu","raw_affiliation_strings":["Department of Medical Information Management, Kaohsiung Medical University, Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Medical Information Management, Kaohsiung Medical University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I152743029"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112137296"],"corresponding_institution_ids":["https://openalex.org/I4210148468"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.15016323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"296","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9984999895095825,"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":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.8445436954498291},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8438969850540161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7765432000160217},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.7526290416717529},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7049325704574585},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6492515802383423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6346700191497803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5181235671043396},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5026299953460693},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.429340124130249},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.42822617292404175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42060402035713196},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.20600441098213196},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15101498365402222},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12269905209541321},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12110543251037598}],"concepts":[{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.8445436954498291},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8438969850540161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765432000160217},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7526290416717529},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7049325704574585},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6492515802383423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6346700191497803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5181235671043396},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5026299953460693},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.429340124130249},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.42822617292404175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42060402035713196},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.20600441098213196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15101498365402222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12269905209541321},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12110543251037598},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W12737881","https://openalex.org/W1482605500","https://openalex.org/W2106780157","https://openalex.org/W2110783210","https://openalex.org/W2134383396","https://openalex.org/W2144125830","https://openalex.org/W2155995145","https://openalex.org/W6628911050"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2432604435","https://openalex.org/W1963976507","https://openalex.org/W2089229568","https://openalex.org/W2019490789","https://openalex.org/W2206035908","https://openalex.org/W3088722891","https://openalex.org/W2790815083"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3,28],"fast":[4],"speaker":[5,55,74],"clustering":[6,75],"method":[7,70,76],"based":[8],"on":[9,48,59],"multidimensional":[10],"scaling.":[11],"Speech":[12],"segments":[13],"are":[14,43,57],"trained":[15,58],"as":[16],"initial":[17],"acoustic":[18,25,54],"models.":[19,40],"MDS":[20,50],"is":[21],"utilized":[22],"to":[23,27],"transform":[24],"models":[26,56],"space":[29],"with":[30],"the":[31,35,49,53,68,72],"coordinate":[32],"best":[33],"preserve":[34],"distances":[36],"or":[37],"dissimilarity":[38],"between":[39],"Speaker":[41],"clusters":[42],"clustered":[44],"using":[45],"vector":[46],"quantization":[47],"coordinates":[51],"and":[52],"MFCCs":[60],"features":[61],"for":[62],"each":[63],"cluster.":[64],"Experimental":[65],"results":[66],"show":[67],"proposed":[69],"outperforms":[71],"baseline":[73],"in":[77],"lower":[78],"execution":[79],"time.":[80]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}