{"id":"https://openalex.org/W2102910419","doi":"https://doi.org/10.1109/icassp.2012.6288853","title":"Robust feature front-end for speaker identification","display_name":"Robust feature front-end for speaker identification","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2102910419","doi":"https://doi.org/10.1109/icassp.2012.6288853","mag":"2102910419"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288853","doi":"https://doi.org/10.1109/icassp.2012.6288853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288853","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"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/A5100412456","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0002-6439-3195","observed_orcids":["https://orcid.org/0000-0002-6439-3195"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Liu","raw_affiliation_strings":["CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, 75083, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, 75083, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078","observed_orcids":["https://orcid.org/0000-0003-4572-6078"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, 75083, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, 75083, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, 75083, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas, Richardson, 75083, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.6913,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9152894,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4233","last_page":"4236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0034000000450760126,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.968999981880188},{"id":"https://openalex.org/keywords/robust-feature-extraction","display_name":"robust feature extraction","score":0.746999979019165},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7799999713897705},{"id":"https://openalex.org/keywords/channel-mismatch","display_name":"channel mismatch","score":0.9850000143051147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675139307975769},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6879764795303345},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6784896850585938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6229479908943176},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5643543004989624},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.559302031993866},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5389407873153687},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5358957052230835},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5297753810882568},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5124269127845764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5013277530670166},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4921059012413025},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.48253509402275085},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.45116686820983887},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44442513585090637},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4185205101966858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40580445528030396},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09387585520744324},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288853","doi":"https://doi.org/10.1109/icassp.2012.6288853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288853","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W40124310","https://openalex.org/W192324892","https://openalex.org/W1490504384","https://openalex.org/W1536018579","https://openalex.org/W1569592550","https://openalex.org/W2051195460","https://openalex.org/W2063656732","https://openalex.org/W2121178298","https://openalex.org/W2144600569","https://openalex.org/W2154354834","https://openalex.org/W2397634864","https://openalex.org/W3022906761","https://openalex.org/W3186851455","https://openalex.org/W4299576595","https://openalex.org/W6843883754"],"related_works":["https://openalex.org/W2086723405","https://openalex.org/W2074262827","https://openalex.org/W2398177287","https://openalex.org/W2793292381","https://openalex.org/W2128319908","https://openalex.org/W46095808","https://openalex.org/W2002341000","https://openalex.org/W2103755349","https://openalex.org/W2363478192","https://openalex.org/W2102346872"],"abstract_inverted_index":{"One":[0],"important":[1],"challenge":[2],"for":[3,23,52,60],"speaker":[4,67],"identification":[5],"(SID)":[6],"system":[7],"is":[8,44],"sustained":[9],"performance":[10,102],"in":[11,25,125],"diverse":[12,116],"conditions.":[13,31,118],"This":[14],"study":[15],"presents":[16],"a":[17],"novel":[18],"front-end":[19],"feature":[20,43,107],"extraction":[21],"method":[22],"SID":[24],"clean,":[26],"noisy,":[27],"and":[28,81,95,110,130],"channel-mismatched":[29],"acoustic":[30],"To":[32],"address":[33],"the":[34,36,71,96,126],"problem,":[35],"perceptual":[37],"minimum":[38],"variance":[39],"distortionless":[40],"response":[41],"(PMVDR)":[42],"employed.":[45],"While":[46],"PMVDR":[47,94,109],"has":[48,56],"been":[49,58],"successfully":[50],"used":[51],"noisy":[53],"ASR,":[54],"it":[55],"not":[57],"considered":[59],"SID.":[61],"We":[62],"also":[63],"incorporate":[64],"longer":[65],"temporal":[66],"knowledge":[68],"based":[69],"on":[70],"shifted":[72],"delta":[73],"cepstral":[74],"(SDC)":[75],"algorithm.":[76],"The":[77],"evaluation":[78],"over":[79],"YOHO":[80],"another":[82],"new":[83],"diversified":[84],"Robust":[85],"Open-Set":[86],"Speaker":[87],"Identification":[88],"(ROSSI)":[89],"database":[90],"show":[91],"that":[92],"both":[93],"union":[97],"with":[98,105],"SDC":[99],"can":[100,121],"improve":[101],"significantly.":[103],"Compared":[104],"traditional":[106],"extraction,":[108],"PMVDR-SDC":[111,120],"always":[112],"give":[113],"improvement":[114,124],"across":[115],"adverse":[117],"Also,":[119],"contribute":[122],"additional":[123],"presence":[127],"of":[128],"noise":[129],"channel":[131],"mismatch.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}
