{"id":"https://openalex.org/W3141035251","doi":"https://doi.org/10.21437/interspeech.2021-1570","title":"Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification","display_name":"Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3141035251","doi":"https://doi.org/10.21437/interspeech.2021-1570","mag":"3141035251"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.02370","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022199264","display_name":"Jenthe Thienpondt","orcid":"https://orcid.org/0000-0001-5990-722X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jenthe Thienpondt","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032699386","display_name":"Brecht Desplanques","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Brecht Desplanques","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Demuynck","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2302","last_page":"2306"},"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":0.9973000288009644,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.8186473846435547},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5596994757652283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5185250043869019},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5139243602752686},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5089235305786133},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5020709037780762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49664002656936646},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.49415329098701477},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4518628716468811},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44185951352119446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44170594215393066},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4365033507347107},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4200814366340637},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12227782607078552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186473846435547},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5596994757652283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185250043869019},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5139243602752686},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5089235305786133},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5020709037780762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49664002656936646},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.49415329098701477},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4518628716468811},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44185951352119446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44170594215393066},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4365033507347107},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4200814366340637},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12227782607078552},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2021-1570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.02370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02370","pdf_url":"https://arxiv.org/pdf/2104.02370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:8720781","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8720781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.02370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02370","pdf_url":"https://arxiv.org/pdf/2104.02370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2157161740","https://openalex.org/W2170088868","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2613904329","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2969985801","https://openalex.org/W2972441390","https://openalex.org/W2991951409","https://openalex.org/W2996132597","https://openalex.org/W3008703194","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3030437843","https://openalex.org/W3042801391","https://openalex.org/W3093582452","https://openalex.org/W3094374485","https://openalex.org/W3109225549","https://openalex.org/W3129012257","https://openalex.org/W4286981691","https://openalex.org/W4300685083","https://openalex.org/W4309845474","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"This":[0,18],"paper":[1],"describes":[2],"the":[3,7,11,33,66,91,121,151,163,168,178,187],"IDLab":[4],"submission":[5],"for":[6],"text-independent":[8],"task":[9],"of":[10,35,38,68,90,94,141],"Short-duration":[12],"Speaker":[13],"Verification":[14],"Challenge":[15],"2021":[16],"(SdSVC-21).":[17],"speaker":[19,57],"verification":[20],"competition":[21],"focuses":[22],"on":[23,162],"short":[24],"duration":[25],"test":[26,171],"recordings":[27],"and":[28,51,65,167],"cross-lingual":[29],"trials,":[30],"along":[31,120],"with":[32],"constraint":[34],"limited":[36],"availability":[37],"in-domain":[39],"DeepMine":[40],"Farsi":[41],"training":[42],"data.":[43],"Currently,":[44],"both":[45],"Time":[46],"Delay":[47],"Neural":[48],"Networks":[49],"(TDNNs)":[50],"ResNets":[52],"achieve":[53],"state-of-the-art":[54],"results":[55],"in":[56,82,111,186],"verification.":[58],"These":[59,115],"architectures":[60,156,181],"are":[61],"structurally":[62],"very":[63],"different":[64],"construction":[67],"hybrid":[69,101],"networks":[70],"looks":[71],"a":[72,78,83,95,127,138,183],"promising":[73],"way":[74,129],"forward.":[75],"We":[76,135],"introduce":[77],"2D":[79],"convolutional":[80],"stem":[81],"strong":[84,92],"ECAPA-TDNN":[85],"baseline":[86,161],"to":[87,99,130],"transfer":[88],"some":[89],"characteristics":[93],"ResNet":[96],"based":[97],"model":[98],"this":[100,125],"CNN-TDNN":[102],"architecture.":[103,114],"Similarly,":[104],"we":[105],"incorporate":[106],"absolute":[107],"frequency":[108,122,132],"positional":[109,133],"encodings":[110],"an":[112],"SE-ResNet34":[113],"learnable":[116],"feature":[117,152],"map":[118],"biases":[119],"axis":[123],"offer":[124],"architecture":[126],"straightforward":[128],"exploit":[131],"information.":[134],"also":[136],"propose":[137],"frequency-wise":[139],"variant":[140],"Squeeze-Excitation":[142],"(SE)":[143],"which":[144],"better":[145],"preserves":[146],"frequency-specific":[147],"information":[148],"when":[149],"rescaling":[150],"maps.":[153],"Both":[154],"modified":[155],"significantly":[157],"outperform":[158],"their":[159],"corresponding":[160],"SdSVC-21":[164,189],"evaluation":[165],"data":[166],"original":[169],"VoxCeleb1":[170],"set.":[172],"A":[173],"four":[174],"system":[175],"fusion":[176],"containing":[177],"two":[179],"improved":[180],"achieved":[182],"third":[184],"place":[185],"final":[188],"Task":[190],"2":[191],"ranking.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-04-13T00:00:00"}