{"id":"https://openalex.org/W2115333237","doi":"https://doi.org/10.21437/interspeech.2006-164","title":"Speaker cluster based GMM tokenization for speaker recognition","display_name":"Speaker cluster based GMM tokenization for speaker recognition","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W2115333237","doi":"https://doi.org/10.21437/interspeech.2006-164","mag":"2115333237"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-164","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100892222","display_name":"Donglai Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Donglai Zhu","raw_affiliation_strings":["Agency for Science, Technology and Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055221016","display_name":"Rong Tong","orcid":"https://orcid.org/0000-0003-3410-8354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3314,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8959866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"paper 1429","last_page":"Mon3A1O.4"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9944999814033508,"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":0.9894000291824341,"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/computer-science","display_name":"Computer science","score":0.7937909960746765},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7635771036148071},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.735968291759491},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7222999930381775},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6995591521263123},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.595215916633606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5575554966926575},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5567559003829956},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5351499319076538},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5253288745880127},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5214475989341736},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4873660206794739},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.4695119559764862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937909960746765},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7635771036148071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.735968291759491},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7222999930381775},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6995591521263123},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.595215916633606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575554966926575},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5567559003829956},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5351499319076538},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5253288745880127},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5214475989341736},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4873660206794739},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4695119559764862}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-164","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"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":11,"referenced_works":["https://openalex.org/W205402702","https://openalex.org/W1982122133","https://openalex.org/W1993482042","https://openalex.org/W2041823554","https://openalex.org/W2095501777","https://openalex.org/W2134815611","https://openalex.org/W2153849757","https://openalex.org/W2156909104","https://openalex.org/W2162273278","https://openalex.org/W2172287020","https://openalex.org/W2407803946"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2206035908","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W1992796048","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2129090883"],"abstract_inverted_index":{"We":[0,115],"present":[1],"a":[2,30,52,77,85,96],"speaker":[3,31,44,53,142,144],"recognition":[4],"system":[5],"with":[6],"multiple":[7,60],"GMM":[8,21,61,127,146],"tokenizers":[9,62,75,128],"as":[10,17,107],"the":[11,18,24,33,36,43,74,100,108,112,117,135],"front-end,":[12],"and":[13,26,47,129,132],"vector":[14,86],"space":[15],"modeling":[16],"back-end":[19,109],"classifier.":[20],"tokenizer":[22],"captures":[23],"acoustic":[25],"phonetic":[27,39],"characteristics":[28,45],"of":[29,38,73,87,111],"from":[32],"speech":[34],"without":[35],"need":[37],"transcription.":[40],"To":[41],"enhance":[42],"coverage":[46],"provide":[48],"more":[49],"discriminative":[50],"information,":[51],"clustering":[54],"algorithm":[55],"is":[56,81,105],"proposed":[57],"to":[58,94],"build":[59],"that":[63],"are":[64,92],"arranged":[65],"in":[66],"parallel.":[67],"For":[68],"an":[69],"input":[70],"utterance,":[71],"each":[72],"outputs":[76],"token":[78],"sequence,":[79],"which":[80],"then":[82],"represented":[83],"by":[84],"n-gram":[88],"probabilities.":[89],"Multiple":[90],"vectors":[91],"concatenated":[93],"form":[95],"composite":[97,113],"vector.":[98],"Finally":[99],"Support":[101],"Vector":[102],"Machine":[103],"(SVM)":[104],"used":[106],"classifier":[110],"vectors.":[114],"use":[116],"2002":[118],"NIST":[119,137],"Speaker":[120],"Recognition":[121],"Evaluation":[122],"(SRE)":[123],"corpus":[124],"for":[125],"training":[126],"background":[130],"modeling,":[131],"evaluate":[133],"on":[134],"2001":[136],"SRE":[138],"corpus.":[139],"Index":[140],"Terms:":[141],"recognition,":[143],"clustering,":[145],"tokenization":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"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"}