{"id":"https://openalex.org/W2061140267","doi":"https://doi.org/10.1109/tasl.2012.2186803","title":"CASA-Based Robust Speaker Identification","display_name":"CASA-Based Robust Speaker Identification","publication_year":2012,"publication_date":"2012-02-03","ids":{"openalex":"https://openalex.org/W2061140267","doi":"https://doi.org/10.1109/tasl.2012.2186803","mag":"2061140267"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2186803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2186803","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/A5102205042","display_name":"Xiaojia Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojia Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079984408","display_name":"Yang Shao","orcid":"https://orcid.org/0000-0002-4870-7406"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Shao","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":9.5035,"has_fulltext":false,"cited_by_count":156,"citation_normalized_percentile":{"value":0.98980579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"20","issue":"5","first_page":"1608","last_page":"1616"},"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":0.9987000226974487,"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/speech-recognition","display_name":"Speech recognition","score":0.8009034991264343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7764102220535278},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.7644378542900085},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.7236984372138977},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5937387943267822},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5870676040649414},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.5499075651168823},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.538478672504425},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5102431774139404},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4972248375415802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4915481507778168},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4908662438392639},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4833764433860779},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48114144802093506},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4723321497440338},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4551042318344116},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4226991832256317},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.34903985261917114},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20505064725875854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09790736436843872}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8009034991264343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764102220535278},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.7644378542900085},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.7236984372138977},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5937387943267822},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5870676040649414},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.5499075651168823},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.538478672504425},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5102431774139404},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4972248375415802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4915481507778168},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4908662438392639},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4833764433860779},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48114144802093506},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4723321497440338},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4551042318344116},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4226991832256317},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.34903985261917114},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20505064725875854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09790736436843872},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2012.2186803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2186803","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"},{"id":"pmh:oai:etd.ohiolink.edu:osu1402620178","is_oa":false,"landing_page_url":"http://rave.ohiolink.edu/etdc/view?acc_num=osu1402620178","pdf_url":null,"source":{"id":"https://openalex.org/S4377196344","display_name":"OhioLink ETD Center (Ohio Library and Information Network)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210155183","host_organization_name":"Ohio Library and Information Network","host_organization_lineage":["https://openalex.org/I4210155183"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rave.ohiolink.edu/etdc/view?acc_num=osu1402620178","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.387","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/ZSW.taslp12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":119,"referenced_works":["https://openalex.org/W3703470","https://openalex.org/W17749540","https://openalex.org/W71792008","https://openalex.org/W95717433","https://openalex.org/W97107628","https://openalex.org/W123426918","https://openalex.org/W140549394","https://openalex.org/W160800111","https://openalex.org/W204053250","https://openalex.org/W264546557","https://openalex.org/W752468880","https://openalex.org/W1492587309","https://openalex.org/W1538905335","https://openalex.org/W1539017161","https://openalex.org/W1575829986","https://openalex.org/W1639266067","https://openalex.org/W1766888123","https://openalex.org/W1888813847","https://openalex.org/W1951870577","https://openalex.org/W1963970749","https://openalex.org/W1967590528","https://openalex.org/W1973746598","https://openalex.org/W1974387177","https://openalex.org/W1989364685","https://openalex.org/W1989674379","https://openalex.org/W1991139021","https://openalex.org/W1991646723","https://openalex.org/W2003146687","https://openalex.org/W2006384862","https://openalex.org/W2007266108","https://openalex.org/W2007645738","https://openalex.org/W2013020033","https://openalex.org/W2023840531","https://openalex.org/W2027804983","https://openalex.org/W2031834500","https://openalex.org/W2034329102","https://openalex.org/W2041823554","https://openalex.org/W2044063703","https://openalex.org/W2047919706","https://openalex.org/W2060822897","https://openalex.org/W2066755975","https://openalex.org/W2069883713","https://openalex.org/W2069976350","https://openalex.org/W2070432038","https://openalex.org/W2072184010","https://openalex.org/W2074262827","https://openalex.org/W2074354966","https://openalex.org/W2075606107","https://openalex.org/W2079362249","https://openalex.org/W2085191029","https://openalex.org/W2086139506","https://openalex.org/W2088361146","https://openalex.org/W2088848997","https://openalex.org/W2096496615","https://openalex.org/W2102346872","https://openalex.org/W2103253424","https://openalex.org/W2103825654","https://openalex.org/W2105092968","https://openalex.org/W2105393821","https://openalex.org/W2106051978","https://openalex.org/W2106934198","https://openalex.org/W2107638917","https://openalex.org/W2108948497","https://openalex.org/W2109761419","https://openalex.org/W2110322414","https://openalex.org/W2115129089","https://openalex.org/W2117678320","https://openalex.org/W2118479009","https://openalex.org/W2119599673","https://openalex.org/W2119901478","https://openalex.org/W2121061347","https://openalex.org/W2122982914","https://openalex.org/W2123157731","https://openalex.org/W2123879651","https://openalex.org/W2126622418","https://openalex.org/W2128653836","https://openalex.org/W2129066450","https://openalex.org/W2129244720","https://openalex.org/W2129379984","https://openalex.org/W2130283666","https://openalex.org/W2131753991","https://openalex.org/W2133095132","https://openalex.org/W2136922672","https://openalex.org/W2137075158","https://openalex.org/W2139959413","https://openalex.org/W2142328794","https://openalex.org/W2143855671","https://openalex.org/W2147147599","https://openalex.org/W2147442641","https://openalex.org/W2147455188","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2151589456","https://openalex.org/W2152131029","https://openalex.org/W2153485077","https://openalex.org/W2154278880","https://openalex.org/W2155680790","https://openalex.org/W2157685287","https://openalex.org/W2157906748","https://openalex.org/W2164432048","https://openalex.org/W2165237516","https://openalex.org/W2166817508","https://openalex.org/W2168379380","https://openalex.org/W2168793898","https://openalex.org/W2170825946","https://openalex.org/W2171225845","https://openalex.org/W2343218625","https://openalex.org/W2403389749","https://openalex.org/W2468858848","https://openalex.org/W2478884216","https://openalex.org/W2550493152","https://openalex.org/W2561557072","https://openalex.org/W2970850616","https://openalex.org/W3216401400","https://openalex.org/W4233392025","https://openalex.org/W4256399001","https://openalex.org/W6675700563","https://openalex.org/W6681846431","https://openalex.org/W6683218471"],"related_works":["https://openalex.org/W2362704157","https://openalex.org/W3199891340","https://openalex.org/W133022121","https://openalex.org/W1567098080","https://openalex.org/W2550493152","https://openalex.org/W2345846362","https://openalex.org/W1578900076","https://openalex.org/W2294106860","https://openalex.org/W2517450235","https://openalex.org/W2061140267"],"abstract_inverted_index":{"Conventional":[0],"speaker":[1,32,39,58,66],"recognition":[2],"systems":[3,126],"perform":[4],"poorly":[5],"under":[6,68,127],"noisy":[7,69,74],"conditions.":[8,70],"Inspired":[9],"by":[10,21,89],"auditory":[11,14,49],"perception,":[12],"computational":[13],"scene":[15],"analysis":[16],"(CASA)":[17],"typically":[18],"segregates":[19],"speech":[20],"producing":[22],"a":[23,37,90,109,128],"binary":[24],"time-frequency":[25],"mask.":[26,92],"We":[27,34,93,102],"investigate":[28],"CASA":[29,78,91],"for":[30],"robust":[31],"identification.":[33],"first":[35],"introduce":[36],"novel":[38],"feature,":[40],"gammatone":[41],"frequency":[42],"cepstral":[43],"coefficient":[44],"(GFCC),":[45],"based":[46,112],"on":[47,113],"an":[48],"periphery":[50],"model,":[51],"and":[52,60,80,98,117],"show":[53],"that":[54,95],"this":[55,118],"feature":[56],"captures":[57],"characteristics":[59],"performs":[61],"substantially":[62],"better":[63],"than":[64],"conventional":[65],"features":[67],"To":[71],"deal":[72],"with":[73],"speech,":[75],"we":[76],"apply":[77],"separation":[79],"then":[81],"either":[82],"reconstruct":[83],"or":[84],"marginalize":[85],"corrupted":[86],"components":[87],"indicated":[88],"find":[94],"both":[96],"reconstruction":[97],"marginalization":[99],"are":[100],"effective.":[101],"further":[103],"combine":[104],"the":[105],"two":[106],"methods":[107],"into":[108],"single":[110],"system":[111,119],"their":[114],"complementary":[115],"advantages,":[116],"achieves":[120],"significant":[121],"performance":[122],"improvements":[123],"over":[124],"related":[125],"wide":[129],"range":[130],"of":[131],"signal-to-noise":[132],"ratios.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}