{"id":"https://openalex.org/W2115809627","doi":"https://doi.org/10.1109/icassp.2003.1202295","title":"Vector quantization techniques for GMM based speaker verification","display_name":"Vector quantization techniques for GMM based speaker verification","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2115809627","doi":"https://doi.org/10.1109/icassp.2003.1202295","mag":"2115809627"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202295","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5041147275","display_name":"Gurkirat Singh","orcid":"https://orcid.org/0000-0003-2995-4193"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"G. Singh","raw_affiliation_strings":["Indian Institute of Technology, Kanpur, India","Indian Institute of Technology , Kanpur , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]},{"raw_affiliation_string":"Indian Institute of Technology , Kanpur , India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067126154","display_name":"Amlana Panda","orcid":"https://orcid.org/0000-0002-9814-1906"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"A. Panda","raw_affiliation_strings":["Centre for High Performance Embedded Systems, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for High Performance Embedded Systems, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003350752","display_name":"Suvanjan Bhattacharyya","orcid":"https://orcid.org/0000-0002-3619-0518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"S. Bhattacharyya","raw_affiliation_strings":["Centre for High Performance Embedded Systems, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for High Performance Embedded Systems, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070475093","display_name":"Thambipillai Srikanthan","orcid":"https://orcid.org/0000-0003-3664-4345"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"T. Srikanthan","raw_affiliation_strings":["Centre for High Performance Embedded Systems, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for High Performance Embedded Systems, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.503,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.89322382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9969000220298767,"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":0.9894999861717224,"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":0.7859293222427368},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.7335437536239624},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.670062243938446},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5960898995399475},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5276300311088562},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5072264671325684},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49481767416000366},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.46859851479530334},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.44932302832603455},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.42802441120147705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3564549684524536},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3538881838321686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3318805694580078},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.21169838309288025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12804725766181946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859293222427368},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7335437536239624},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.670062243938446},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5960898995399475},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5276300311088562},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5072264671325684},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49481767416000366},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.46859851479530334},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.44932302832603455},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.42802441120147705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3564549684524536},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3538881838321686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3318805694580078},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.21169838309288025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12804725766181946},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1202295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202295","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1969674180","https://openalex.org/W2121407732","https://openalex.org/W2134383396","https://openalex.org/W2165880886","https://openalex.org/W2169727582","https://openalex.org/W2907162034","https://openalex.org/W4300956553"],"related_works":["https://openalex.org/W2018623685","https://openalex.org/W2138195696","https://openalex.org/W66821593","https://openalex.org/W2545295736","https://openalex.org/W1521299571","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W4235705411","https://openalex.org/W1992796048","https://openalex.org/W1516392727"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,42,57,62,72,76,79,83,86,89,101,123,160],"novel":[4],"application":[5],"of":[6,44,78,85,109,119,131],"two":[7],"vector":[8],"quantization":[9],"algorithms,":[10],"namely":[11],"Linde,":[12],"Buzo,":[13],"Gray":[14],"(1980)":[15],"and":[16,30,38,68,88,138],"K-means":[17,90,113,139],"algorithm":[18,91,103,162],"for":[19,47,55,141,147,174],"efficient":[20,49,95],"speaker":[21,24,58,145,149],"verification.":[22],"Automatic":[23],"verification":[25],"(ASV)":[26],"is":[27,127],"a":[28],"memory":[29],"compute":[31,94],"intensive":[32],"process,":[33],"giving":[34],"rise":[35],"to":[36,71,92],"area":[37],"latency":[39],"concerns":[40],"in":[41,75],"way":[43],"its":[45],"implementation":[46,77],"real-time":[48],"embedded":[50],"systems.":[51],"The":[52],"training":[53,96,142],"schemes":[54],"computing":[56],"models,":[59],"such":[60],"as":[61,105,107,115,117,159],"expectation":[63],"maximization":[64],"are":[65],"highly":[66],"iterative":[67],"contribute":[69],"significantly":[70,164],"overall":[73],"complexity":[74,126],"system.":[80],"We":[81],"demonstrate":[82],"use":[84],"LBG":[87,102,132,137],"realize":[93],"method.":[97],"Models":[98],"trained":[99],"with":[100],"achieves":[104,114],"much":[106,116],"99.88%":[108],"EM":[110,120,124,161],"accuracy,":[111],"whilst":[112],"99.91%":[118],"accuracy.":[121],"Moreover,":[122],"computational":[125,166],"almost":[128],"twice":[129],"that":[130,154],"or":[133],"K-means.":[134],"Thus,":[135],"using":[136],"algorithms":[140],"Gaussian":[143],"mixture":[144],"models":[146],"text-independent":[148],"verification,":[150],"we":[151],"show":[152],"that,":[153],"they":[155],"deliver":[156],"comparable":[157],"performance":[158],"at":[163],"reduced":[165],"complexity.":[167],"Thus":[168],"making":[169],"them":[170],"an":[171],"ideal":[172],"choice":[173],"low-cost":[175],"applications.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}