{"id":"https://openalex.org/W4380785258","doi":"https://doi.org/10.1109/taslp.2023.3284521","title":"Attention and DCT Based Global Context Modeling for Text-Independent Speaker Recognition","display_name":"Attention and DCT Based Global Context Modeling for Text-Independent Speaker Recognition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4380785258","doi":"https://doi.org/10.1109/taslp.2023.3284521"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3284521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284521","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM 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/A5101861591","display_name":"Wei Xia","orcid":"https://orcid.org/0009-0009-4734-6256"},"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":"Wei Xia","raw_affiliation_strings":["Center for Robust Speech Systems, Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0009-0009-4734-6256","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA","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"},"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":["Center for Robust Speech Systems, Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA","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":1.1922,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82269714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"2668","last_page":"2679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.79912930727005},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6909481883049011},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6349833011627197},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5977869629859924},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5382646322250366},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4916899800300598},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4826222360134125},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.46757772564888},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.427865207195282},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.415690153837204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39892908930778503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37129178643226624},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0982198715209961},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07692286372184753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79912930727005},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6909481883049011},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6349833011627197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5977869629859924},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5382646322250366},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4916899800300598},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4826222360134125},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.46757772564888},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.427865207195282},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.415690153837204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39892908930778503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37129178643226624},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0982198715209961},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07692286372184753},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3284521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284521","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W1902237438","https://openalex.org/W1936725236","https://openalex.org/W2101261946","https://openalex.org/W2121812409","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2292996718","https://openalex.org/W2295590090","https://openalex.org/W2406312423","https://openalex.org/W2460742184","https://openalex.org/W2609675817","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747900149","https://openalex.org/W2752782242","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2884585870","https://openalex.org/W2889278126","https://openalex.org/W2890964092","https://openalex.org/W2908510526","https://openalex.org/W2922509574","https://openalex.org/W2936780106","https://openalex.org/W2938358845","https://openalex.org/W2951758756","https://openalex.org/W2954930822","https://openalex.org/W2962959915","https://openalex.org/W2963091558","https://openalex.org/W2963371159","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2972369255","https://openalex.org/W2972612102","https://openalex.org/W2972806170","https://openalex.org/W2972909277","https://openalex.org/W2973062255","https://openalex.org/W2973193289","https://openalex.org/W2981413347","https://openalex.org/W2982220924","https://openalex.org/W2987108559","https://openalex.org/W2987748894","https://openalex.org/W3013020904","https://openalex.org/W3015261361","https://openalex.org/W3016719260","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3034257218","https://openalex.org/W3034552520","https://openalex.org/W3037100371","https://openalex.org/W3090254849","https://openalex.org/W3096529494","https://openalex.org/W3097244734","https://openalex.org/W3097470351","https://openalex.org/W3103152812","https://openalex.org/W3142516134","https://openalex.org/W3198259309","https://openalex.org/W3217778739","https://openalex.org/W4214666412","https://openalex.org/W4214921663","https://openalex.org/W4226093532","https://openalex.org/W4226184234","https://openalex.org/W4283031701","https://openalex.org/W4286611450","https://openalex.org/W4313387459","https://openalex.org/W6688816777","https://openalex.org/W6697535213","https://openalex.org/W6713727690","https://openalex.org/W6753412334","https://openalex.org/W6757817989","https://openalex.org/W6783527727"],"related_works":["https://openalex.org/W2055682261","https://openalex.org/W1916685473","https://openalex.org/W1993363272","https://openalex.org/W2174937762","https://openalex.org/W2186390138","https://openalex.org/W2790129917","https://openalex.org/W2060035984","https://openalex.org/W2992856432","https://openalex.org/W2329500892","https://openalex.org/W2054459866"],"abstract_inverted_index":{"Learning":[0],"an":[1,137],"effective":[2],"speaker":[3,12,82,93,134,221,232,283],"representation":[4],"is":[5,141,160,177,193],"crucial":[6],"for":[7,133],"achieving":[8,286],"reliable":[9],"performance":[10,234,261],"in":[11,80,118],"verification":[13,233],"tasks.":[14],"Speech":[15],"signals":[16],"are":[17,251],"high-dimensional,":[18],"long,":[19],"and":[20,76,91,103,147,166,208,241,288],"variable-length":[21],"sequences":[22],"that":[23,43,258,271],"entail":[24],"a":[25,88,126,155,220,245],"complex":[26,54],"hierarchical":[27],"structure.":[28],"Signals":[29],"may":[30,259],"contain":[31],"diverse":[32],"information":[33,117,192],"at":[34],"each":[35],"time-frequency":[36,129,152,198,289],"(TF)":[37],"location.":[38],"The":[39,211],"standard":[40,238],"convolutional":[41],"layer":[42],"operates":[44],"on":[45],"neighboring":[46],"local":[47,209],"regions":[48],"often":[49],"fails":[50],"to":[51,64,86,112,143,162,179,195,236,254],"capture":[52,144],"the":[53,62,70,81,98,115,145,168,189,202,205,231,237,263,272,281],"TF":[55],"global":[56,116,128,190,206,274],"information.":[57],"Our":[58,267],"motivation":[59],"stems":[60],"from":[61],"need":[63],"alleviate":[65],"these":[66],"challenges":[67],"by":[68,96,200,244,285],"increasing":[69],"modeling":[71,131,181,276],"capacity,":[72],"emphasizing":[73],"significant":[74],"information,":[75],"suppressing":[77],"possible":[78],"redundancies":[79],"representation.":[83],"We":[84],"aim":[85],"design":[87],"more":[89],"robust":[90],"efficient":[92],"recognition":[94],"system":[95],"incorporating":[97],"benefits":[99,169],"of":[100,170,262],"attention":[101,175],"mechanisms":[102],"Discrete":[104],"Cosine":[105],"Transform":[106],"(DCT)":[107],"based":[108,157],"signal":[109,171],"processing":[110],"techniques,":[111],"effectively":[113,229],"represent":[114],"speech":[119],"signals.":[120],"To":[121],"achieve":[122],"this,":[123],"we":[124],"propose":[125],"general":[127],"context":[130,139,158,191,207,275],"block":[132,243],"modeling.":[135,172],"First,":[136],"attention-based":[138],"model":[140,159,164,222,240],"introduced":[142],"long-range":[146],"non-local":[148],"relationship":[149],"across":[150],"different":[151],"locations.":[153],"Second,":[154],"2D-DCT":[156],"proposed":[161,212,264,273],"improve":[163,180,280],"efficiency":[165],"examine":[167],"A":[173],"multi-DCT":[174],"mechanism":[176],"presented":[178],"power":[182],"with":[183,223],"alternate":[184],"DCT":[185],"base":[186],"forms.":[187],"Finally,":[188],"used":[194],"recalibrate":[196],"salient":[197],"locations":[199],"computing":[201],"similarity":[203],"between":[204],"features.":[210],"lightweight":[213],"blocks":[214],"can":[215,278],"be":[216],"easily":[217],"incorporated":[218],"into":[219],"little":[224],"additional":[225],"computational":[226],"costs.":[227],"This":[228],"improves":[230],"compared":[235],"ResNet":[239],"Squeeze&Excitation":[242],"large":[246],"margin.":[247],"Detailed":[248],"ablation":[249],"studies":[250],"also":[252],"performed":[253],"analyze":[255],"various":[256],"factors":[257],"impact":[260],"individual":[265],"modules.":[266],"experimental":[268],"results":[269],"show":[270],"method":[277],"efficiently":[279],"learned":[282],"representations":[284],"channel-wise":[287],"feature":[290],"recalibration.":[291]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}