{"id":"https://openalex.org/W4226184234","doi":"https://doi.org/10.1109/asru51503.2021.9688243","title":"Duality Temporal-Channel-Frequency Attention Enhanced Speaker Representation Learning","display_name":"Duality Temporal-Channel-Frequency Attention Enhanced Speaker Representation Learning","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226184234","doi":"https://doi.org/10.1109/asru51503.2021.9688243"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688243","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-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/A5100425399","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-5077-9962"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808955","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0008-5449-4815"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100425399"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.754,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75733782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9919999837875366,"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":0.9696999788284302,"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/discriminative-model","display_name":"Discriminative model","score":0.700056791305542},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6872332692146301},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6858710050582886},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6387120485305786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.616718053817749},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5766788721084595},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.5465400815010071},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5155603885650635},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.514407217502594},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49002063274383545},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48878213763237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47346392273902893},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40814775228500366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3959139883518219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.238539457321167},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12184208631515503},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11013561487197876},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09052535891532898},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06176024675369263},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0612315833568573}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.700056791305542},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6872332692146301},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6858710050582886},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6387120485305786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.616718053817749},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5766788721084595},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.5465400815010071},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5155603885650635},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.514407217502594},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49002063274383545},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48878213763237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47346392273902893},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40814775228500366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3959139883518219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.238539457321167},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12184208631515503},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11013561487197876},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09052535891532898},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06176024675369263},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0612315833568573},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688243","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2121750345","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2407080277","https://openalex.org/W2606004785","https://openalex.org/W2726515241","https://openalex.org/W2752782242","https://openalex.org/W2766191375","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2884585870","https://openalex.org/W2890964092","https://openalex.org/W2917756095","https://openalex.org/W2936774411","https://openalex.org/W2962788625","https://openalex.org/W2962959915","https://openalex.org/W2963091558","https://openalex.org/W2964054038","https://openalex.org/W2967957380","https://openalex.org/W2969985801","https://openalex.org/W2972552635","https://openalex.org/W2973190269","https://openalex.org/W2981005517","https://openalex.org/W3010893827","https://openalex.org/W3013020904","https://openalex.org/W3015261361","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3025075133","https://openalex.org/W3090254849","https://openalex.org/W3095079700","https://openalex.org/W3096529494","https://openalex.org/W3114391598","https://openalex.org/W3115366194","https://openalex.org/W3137249133","https://openalex.org/W3141035251","https://openalex.org/W3142516134","https://openalex.org/W3151878189","https://openalex.org/W3160076723","https://openalex.org/W3196560414","https://openalex.org/W4206908380","https://openalex.org/W4288091954","https://openalex.org/W4297810817","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6713311039","https://openalex.org/W6740167877","https://openalex.org/W6753038380","https://openalex.org/W6753412334","https://openalex.org/W6767842233","https://openalex.org/W6769178842","https://openalex.org/W6783527727","https://openalex.org/W6787962620"],"related_works":["https://openalex.org/W4388913932","https://openalex.org/W4309130263","https://openalex.org/W1951490636","https://openalex.org/W3208297503","https://openalex.org/W2905271011","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,67,123,141,150,161,172],"channel-wise":[3,32,63],"attention":[4,33,59,78,82,88,127],"in":[5,15],"CNN":[6],"based":[7],"speaker":[8,16,117],"representation":[9],"networks":[10],"has":[11],"achieved":[12],"remarkable":[13],"performance":[14],"verification":[17],"(SV).":[18],"But":[19],"these":[20],"approaches":[21],"do":[22],"simple":[23],"averaging":[24],"on":[25,70,93,109,128],"time":[26],"and":[27,35,72,99,131,155,166],"frequency":[28,47,73],"feature":[29,101],"maps":[30,102],"before":[31],"learning":[34],"ignore":[36],"the":[37,55,62,76,97,110,121,124,129,135,139,159],"essential":[38],"mutual":[39],"interaction":[40],"among":[41],"temporal,":[42],"channel":[43],"as":[44,46,83,85],"well":[45,84],"scales.":[48],"To":[49],"address":[50],"this":[51],"problem,":[52],"we":[53],"propose":[54],"Duality":[56],"Temporal-Channel-Frequency":[57],"(DTCF)":[58],"to":[60,91,114],"re-calibrate":[61],"features":[64],"with":[65,148,170],"aggregation":[66],"global":[68,111],"context":[69],"temporal":[71],"dimensions.":[74],"Specifically,":[75],"duality":[77],"-":[79,89],"time-channel":[80],"(T-C)":[81],"frequency-channel":[86],"(F-C)":[87],"aims":[90],"focus":[92],"salient":[94],"regions":[95],"along":[96],"T-C":[98],"F-C":[100],"that":[103],"may":[104],"have":[105],"more":[106,115],"considerable":[107],"impact":[108],"context,":[112],"leading":[113],"discriminative":[116],"representations.":[118],"We":[119],"evaluate":[120],"effectiveness":[122],"proposed":[125],"DTCF":[126],"CN-Celeb":[130,136],"VoxCeleb":[132],"datasets.":[133],"On":[134,152],"evaluation":[137,157],"set,":[138],"EER/minDCF":[140,160],"ResNet34-DTCF":[142,162],"are":[143],"reduced":[144],"by":[145],"0.63%/0.0718":[146],"compared":[147,169],"those":[149,171],"ResNet34-SE.":[151,173],"VoxCeleb1-O,":[153],"VoxCeleb1-E":[154],"VoxCeleb1-H":[156],"sets,":[158],"achieve":[163],"0.36%/0.0263,":[164],"0.39%/0.0382":[165],"0.74%/0.0753":[167],"reductions":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}