{"id":"https://openalex.org/W2111225999","doi":"https://doi.org/10.1109/icassp.2006.1660101","title":"Speaker Verification Over Handheld Devices with Realistic Noisy Speech Data","display_name":"Speaker Verification Over Handheld Devices with Realistic Noisy Speech Data","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2111225999","doi":"https://doi.org/10.1109/icassp.2006.1660101","mag":"2111225999"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660101","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":"conference-paper","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/A5101838286","display_name":"Ji Ming","orcid":"https://orcid.org/0000-0001-6887-2591"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ji Ming","raw_affiliation_strings":["School of EECS, Queen's University, Belfast, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Queen's University, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T.J. Hazen","raw_affiliation_strings":["Artficial Intelligence Laboratory, MIT Computer Science, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artficial Intelligence Laboratory, MIT Computer Science, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073966667","display_name":"Jim Glass","orcid":"https://orcid.org/0000-0002-0148-0224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J.R. Glass","raw_affiliation_strings":["Artficial Intelligence Laboratory, MIT Computer Science, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artficial Intelligence Laboratory, MIT Computer Science, Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/headset","display_name":"Headset","score":0.8600757122039795},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8058230876922607},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.786724328994751},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6570733785629272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5637391805648804},{"id":"https://openalex.org/keywords/quiet","display_name":"QUIET","score":0.5496958494186401},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5385241508483887},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5154339075088501},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.45288538932800293},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4519869089126587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3724867105484009},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20977210998535156}],"concepts":[{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.8600757122039795},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058230876922607},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.786724328994751},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6570733785629272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5637391805648804},{"id":"https://openalex.org/C2777185736","wikidata":"https://www.wikidata.org/wiki/Q7265603","display_name":"QUIET","level":2,"score":0.5496958494186401},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5385241508483887},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5154339075088501},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.45288538932800293},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4519869089126587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3724867105484009},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20977210998535156},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660101","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W89083193","https://openalex.org/W95717433","https://openalex.org/W175297027","https://openalex.org/W1551646560","https://openalex.org/W1558317537","https://openalex.org/W1956021273","https://openalex.org/W1977167953","https://openalex.org/W2023840531","https://openalex.org/W2041823554","https://openalex.org/W2052752543","https://openalex.org/W2078953162","https://openalex.org/W2082470439","https://openalex.org/W2099228311","https://openalex.org/W2105360594","https://openalex.org/W2121178298","https://openalex.org/W2128202590","https://openalex.org/W2133233779","https://openalex.org/W2138547132","https://openalex.org/W2397634864","https://openalex.org/W6633151797","https://openalex.org/W6633540372","https://openalex.org/W6644815614","https://openalex.org/W6712325649"],"related_works":["https://openalex.org/W3145885707","https://openalex.org/W2549567669","https://openalex.org/W4319998403","https://openalex.org/W1964830557","https://openalex.org/W4240949492","https://openalex.org/W4300668837","https://openalex.org/W104838418","https://openalex.org/W1532889363","https://openalex.org/W4388398572","https://openalex.org/W2107246453"],"abstract_inverted_index":{"We":[0,43],"study":[1],"speaker":[2,47],"verification":[3,82],"for":[4,130,161],"handheld":[5],"devices":[6],"assuming":[7,13],"realistic,":[8],"noisy":[9,163],"test":[10],"conditions":[11],"and":[12,27,39,55,59,93,96,105,133,156],"no":[14],"prior":[15],"knowledge":[16],"of":[17,35,90,113,123],"the":[18,33,46,52,88,91,106,131,134,137,144],"noise":[19,121,141],"characteristics.":[20,116],"Data":[21],"were":[22,65,151],"recorded":[23],"in":[24,57],"office":[25,53],"(\"quiet\")":[26],"street":[28],"intersection":[29],"(\"noisy\")":[30],"environments,":[31],"with":[32],"use":[34],"an":[36,40],"internal":[37],"microphone":[38],"external":[41],"headset.":[42],"assume":[44],"that":[45,80,101],"models":[48,150],"are":[49],"trained":[50],"using":[51,119],"data":[54,122],"tested":[56],"matched":[58],"mismatched":[60],"environment/microphone":[61],"conditions.":[62,147],"Two":[63],"approaches":[64],"studied,":[66],"both":[67],"built":[68],"upon":[69],"a":[70,75,127],"subband":[71],"feature":[72],"framework:":[73],"1)":[74],"posterior":[76],"union":[77],"model":[78],"(PUM)":[79],"focuses":[81],"on":[83],"matching":[84],"subbands":[85],"thereby":[86],"reducing":[87],"effect":[89],"training":[92,104,118,146],"testing":[94],"mismatch,":[95],"2)":[97],"universal":[98],"compensation":[99,129,138],"(UC)":[100],"combines":[102],"multi-condition":[103],"PUM":[107,135],"to":[108,111,153],"provide":[109],"robustness":[110,160],"noises":[112],"arbitrary":[114],"temporal-spectral":[115],"Multi-condition":[117],"simulated":[120],"different":[124],"characteristics":[125],"provides":[126],"\"coarse\"":[128],"noise,":[132],"refines":[136],"by":[139],"ignoring":[140],"variations":[142],"outside":[143],"given":[145],"These":[148],"two":[149],"compared":[152],"baseline":[154],"systems":[155],"have":[157],"shown":[158],"improved":[159],"realistic":[162],"speech":[164],"data.":[165]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
