{"id":"https://openalex.org/W2171903461","doi":"https://doi.org/10.1109/tasl.2010.2101594","title":"An Auditory-Based Feature Extraction Algorithm for Robust Speaker Identification Under Mismatched Conditions","display_name":"An Auditory-Based Feature Extraction Algorithm for Robust Speaker Identification Under Mismatched Conditions","publication_year":2010,"publication_date":"2010-12-23","ids":{"openalex":"https://openalex.org/W2171903461","doi":"https://doi.org/10.1109/tasl.2010.2101594","mag":"2171903461"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2101594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2101594","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100350165","display_name":"Qi Li","orcid":"https://orcid.org/0000-0001-8776-8730"},"institutions":[{"id":"https://openalex.org/I4210098935","display_name":"Li Creative Technologies (United States)","ror":"https://ror.org/010hpfk35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098935"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qi Li","raw_affiliation_strings":["Creative Technologies, Inc., Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Creative Technologies, Inc., Florham Park, NJ, USA","institution_ids":["https://openalex.org/I4210098935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100764456","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-0575-0156"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100350165"],"corresponding_institution_ids":["https://openalex.org/I4210098935"],"apc_list":null,"apc_paid":null,"fwci":4.0456,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.94669952,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"19","issue":"6","first_page":"1791","last_page":"1801"},"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":0.9997000098228455,"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":0.9973000288009644,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7809112668037415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5998091101646423},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5484635233879089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5441161394119263},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5327038168907166},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.4422055184841156},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4336083233356476},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.41070666909217834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3594304919242859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34367164969444275},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09041228890419006}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7809112668037415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5998091101646423},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5484635233879089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5441161394119263},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5327038168907166},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.4422055184841156},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4336083233356476},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.41070666909217834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3594304919242859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34367164969444275},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09041228890419006},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2101594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2101594","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W135906098","https://openalex.org/W1502084087","https://openalex.org/W1536990986","https://openalex.org/W1966264494","https://openalex.org/W1971971342","https://openalex.org/W1973295469","https://openalex.org/W1988730256","https://openalex.org/W1992468098","https://openalex.org/W1995453281","https://openalex.org/W2008806652","https://openalex.org/W2013020033","https://openalex.org/W2024158325","https://openalex.org/W2029654180","https://openalex.org/W2050693797","https://openalex.org/W2055120733","https://openalex.org/W2056703060","https://openalex.org/W2062124357","https://openalex.org/W2069723558","https://openalex.org/W2074724960","https://openalex.org/W2090861223","https://openalex.org/W2091353249","https://openalex.org/W2091735899","https://openalex.org/W2096471577","https://openalex.org/W2102346872","https://openalex.org/W2105316407","https://openalex.org/W2109225367","https://openalex.org/W2118299326","https://openalex.org/W2118300874","https://openalex.org/W2122516409","https://openalex.org/W2137075158","https://openalex.org/W2143331764","https://openalex.org/W2148154194","https://openalex.org/W2153997542","https://openalex.org/W2165880886","https://openalex.org/W2167591993","https://openalex.org/W2295355370","https://openalex.org/W2520367123","https://openalex.org/W4233392025","https://openalex.org/W4234947109","https://openalex.org/W6605478764","https://openalex.org/W6667783703","https://openalex.org/W6675700563"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W2387604097","https://openalex.org/W1980297060","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W4317383455","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2548511587"],"abstract_inverted_index":{"An":[0],"auditory-based":[1],"feature":[2],"extraction":[3],"algorithm":[4],"is":[5,143],"presented.":[6],"We":[7],"name":[8],"the":[9,36,41,55,65,96,103,135,140,146,149,156,192,206],"new":[10],"features":[11,45,83,98,106,128,151,158,168,182,194,208],"as":[12],"cochlear":[13],"filter":[14],"cepstral":[15],"coefficients":[16],"(CFCCs)":[17],"which":[18],"are":[19,46,195],"defined":[20],"based":[21],"on":[22],"a":[23,30,49],"recently":[24],"developed":[25],"auditory":[26],"transform":[27],"(AT)":[28],"plus":[29],"set":[31],"of":[32,67,91,139,148,163],"modules":[33],"to":[34,48,53,153,172,212],"emulate":[35],"signal":[37,142],"processing":[38],"functions":[39],"in":[40,71,78,88,121],"cochlea.":[42],"The":[43,81,165,180],"CFCC":[44,82,97,127,157,167,181,193,207],"applied":[47],"speaker":[50],"identification":[51],"task":[52],"address":[54],"acoustic":[56,68],"mismatch":[57],"problem":[58],"between":[59],"training":[60],"and":[61,116,126,177,203],"testing":[62,111],"environments.":[63],"Usually,":[64],"performance":[66],"models":[69],"trained":[70],"clean":[72,122],"speech":[73],"drops":[74,152],"significantly":[75,196],"when":[76,134],"tested":[77],"noisy":[79],"speech.":[80],"have":[84],"shown":[85],"strong":[86],"robustness":[87],"this":[89],"kind":[90],"situation.":[92],"In":[93],"our":[94],"experiments,":[95],"consistently":[99,183],"perform":[100,129,184],"better":[101,186,197],"than":[102,187,198],"baseline":[104],"MFCC":[105,125,150],"under":[107,201],"all":[108],"three":[109],"mismatched":[110],"conditions-white":[112],"noise,":[113,115,191,205],"car":[114,202],"babble":[117,204],"noise.":[118],"For":[119],"example,":[120],"conditions,":[123],"both":[124],"similarly,":[130],"over":[131],"96%,":[132],"but":[133],"signal-to-noise":[136],"ratio":[137],"(SNR)":[138],"input":[141],"6":[144],"dB,":[145],"accuracy":[147,162],"41.2%,":[154],"while":[155,200],"still":[159],"achieve":[160],"an":[161],"88.3%.":[164],"proposed":[166],"also":[169],"compare":[170],"favorably":[171],"perceptual":[173],"linear":[174],"predictive":[175],"(PLP)":[176],"RASTA-PLP":[178],"features.":[179],"much":[185],"PLP.":[188],"Under":[189],"white":[190],"RASTA-PLP,":[199],"provide":[209],"similar":[210],"performances":[211],"RASTA-PLP.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}