{"id":"https://openalex.org/W2127860162","doi":"https://doi.org/10.1109/icassp.2006.1660105","title":"QUANTization for Adapted GMM-Based Speaker Verification","display_name":"QUANTization for Adapted GMM-Based Speaker Verification","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2127860162","doi":"https://doi.org/10.1109/icassp.2006.1660105","mag":"2127860162"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660105","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/A5064407975","display_name":"Ivy H. Tseng","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I.H. Tseng","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA","Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111987698","display_name":"O. Verscheure","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"O. Verscheure","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056925015","display_name":"Deepak S. Turaga","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.S. Turaga","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111344355","display_name":"U.V. Chaudhari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"U.V. Chaudhari","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8651,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87825836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"653"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9708999991416931,"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/computer-science","display_name":"Computer science","score":0.680645227432251},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6195213794708252},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6002732515335083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5861839652061462},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5211841464042664},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4905526041984558},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4893333315849304},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4588582515716553},{"id":"https://openalex.org/keywords/likelihood-ratio-test","display_name":"Likelihood-ratio test","score":0.4302371144294739},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42097824811935425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4209282696247101},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41956573724746704},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3819318413734436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3387182950973511},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2875237464904785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23005136847496033},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13924473524093628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680645227432251},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6195213794708252},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6002732515335083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5861839652061462},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5211841464042664},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4905526041984558},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4893333315849304},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4588582515716553},{"id":"https://openalex.org/C9483764","wikidata":"https://www.wikidata.org/wiki/Q585740","display_name":"Likelihood-ratio test","level":2,"score":0.4302371144294739},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42097824811935425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4209282696247101},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41956573724746704},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3819318413734436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3387182950973511},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2875237464904785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23005136847496033},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13924473524093628},{"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},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1660105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660105","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:10.1.1.332.4539","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.4539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://biron.usc.edu/~hsinyits/Papers/ICASSP06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2041823554","https://openalex.org/W2124002824","https://openalex.org/W2139037446"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2432604435","https://openalex.org/W2048014685","https://openalex.org/W2511460115","https://openalex.org/W2370972896","https://openalex.org/W2089229568","https://openalex.org/W2019490789","https://openalex.org/W3088722891"],"abstract_inverted_index":{"State-of-the-art":[0],"speaker":[1,26,36,134],"verification":[2,135,147],"systems":[3],"are":[4],"built":[5],"around":[6],"the":[7,39,48,61,69,79,87,99,105,108,114,117,130,140,171],"likelihood":[8,17],"ratio":[9,67],"test,":[10],"using":[11],"Gaussian":[12,90],"mixture":[13],"models":[14,37],"(GMM)":[15],"for":[16,24,53,86,149],"functions,":[18],"a":[19,29],"universal":[20],"background":[21],"model":[22],"(UBM)":[23],"alternative":[25],"representation,":[27],"and":[28,71,122],"form":[30],"of":[31,47,63,65,107,116],"Bayesian":[32],"adaptation":[33],"to":[34,165],"derive":[35,98],"from":[38],"UBM.":[40],"This":[41],"work":[42],"tackles":[43],"optimal":[44,92,100],"quantizer":[45,85],"design":[46],"speech":[49,73],"cepstral":[50],"features":[51],"(MFCCs)":[52],"such":[54],"systems.":[55],"The":[56],"problem":[57],"is":[58,91],"posed":[59],"as":[60,152,154],"minimization":[62],"loss":[64],"log-likelihood":[66],"between":[68],"quantized":[70],"unquantized":[72],"features.":[74],"First":[75],"we":[76,97,112],"show":[77,143],"that":[78],"conventional":[80],"mean":[81],"squared":[82],"error":[83],"(MSE)":[84],"top-scoring":[88],"UBM":[89],"under":[93],"practical":[94],"assumptions.":[95],"Then":[96],"bit":[101,123,150,158],"allocation":[102,124],"strategy":[103],"across":[104],"dimensions":[106],"feature":[109],"vectors.":[110],"Finally":[111],"demonstrate":[113],"validity":[115],"approach":[118],"against":[119],"various":[120],"quantization":[121],"schemes":[125],"by":[126],"running":[127],"experiments":[128],"on":[129,139,146,161],"appropriately":[131],"modified":[132],"IBM":[133],"system.":[136],"Experimental":[137],"results":[138],"HUB4":[141],"corpora":[142],"negligible":[144],"impact":[145],"performance":[148],"rates":[151],"low":[153],"less":[155],"than":[156],"1":[157],"per":[159,168],"dimension":[160,169],"average":[162],"in":[163,170],"contrast":[164],"32":[166],"bits":[167],"original":[172],"system":[173]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}