{"id":"https://openalex.org/W4394565150","doi":"https://doi.org/10.1016/j.procs.2024.03.211","title":"Optimizing Speaker Identification through SincsquareNet and SincNet Fusion with Attention Mechanism","display_name":"Optimizing Speaker Identification through SincsquareNet and SincNet Fusion with Attention Mechanism","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394565150","doi":"https://doi.org/10.1016/j.procs.2024.03.211"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2024.03.211","doi":"https://doi.org/10.1016/j.procs.2024.03.211","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2024.03.211","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2024.03.211","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012289707","display_name":"Banala Saritha","orcid":"https://orcid.org/0000-0002-6499-3561","observed_orcids":["https://orcid.org/0000-0002-6499-3561"]},"institutions":[{"id":"https://openalex.org/I151903974","display_name":"National Institute Of Technology Silchar","ror":"https://ror.org/001ws2a36","country_code":"IN","type":"education","lineage":["https://openalex.org/I151903974"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Banala Saritha","raw_affiliation_strings":["Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam, 788010, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam, 788010, India","institution_ids":["https://openalex.org/I151903974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000303933","display_name":"Rabul Hussain Laskar","orcid":"https://orcid.org/0000-0003-3988-394X","observed_orcids":["https://orcid.org/0000-0003-3988-394X"]},"institutions":[{"id":"https://openalex.org/I151903974","display_name":"National Institute Of Technology Silchar","ror":"https://ror.org/001ws2a36","country_code":"IN","type":"education","lineage":["https://openalex.org/I151903974"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rabul Hussain Laskar","raw_affiliation_strings":["Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam, 788010, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam, 788010, India","institution_ids":["https://openalex.org/I151903974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110531919","display_name":"Madhuchhanda Choudhury","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I151903974","display_name":"National Institute Of Technology Silchar","ror":"https://ror.org/001ws2a36","country_code":"IN","type":"education","lineage":["https://openalex.org/I151903974"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Madhuchhanda Choudhury","raw_affiliation_strings":["Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam, 788010, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam, 788010, India","institution_ids":["https://openalex.org/I151903974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004515690","display_name":"Anish Monsley Kirupakaran","orcid":"https://orcid.org/0000-0002-4927-3785","observed_orcids":["https://orcid.org/0000-0002-4927-3785"]},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anish Monsley K","raw_affiliation_strings":["Department of Applied Mechanics and Biomedical Engineering, Indian Institute of Technology, Madras, 600036, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mechanics and Biomedical Engineering, Indian Institute of Technology, Madras, 600036, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000303933","https://openalex.org/A5004515690","https://openalex.org/A5012289707","https://openalex.org/A5110531919"],"corresponding_institution_ids":["https://openalex.org/I151903974","https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":2.9011,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93060061,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"233","issue":null,"first_page":"215","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0007999999797903001,"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":9.999999747378752e-05,"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/speaker-identification","display_name":"speaker identification","score":0.9959999918937683},{"id":"https://openalex.org/keywords/sincnet","display_name":"SincNet","score":0.9169999957084656},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.5220000147819519},{"id":"https://openalex.org/keywords/model-fusion","display_name":"model fusion","score":0.6259999871253967},{"id":"https://openalex.org/keywords/speech-feature-extraction","display_name":"speech feature extraction","score":0.6209999918937683},{"id":"https://openalex.org/keywords/librispeech","display_name":"LibriSpeech","score":0.6129999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9354388117790222},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6941759586334229},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6702513098716736},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6417083144187927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5369811654090881},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4969077408313751},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48811468482017517},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4392687976360321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3734368085861206},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08765500783920288},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2024.03.211","doi":"https://doi.org/10.1016/j.procs.2024.03.211","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2024.03.211","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2024.03.211","doi":"https://doi.org/10.1016/j.procs.2024.03.211","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2024.03.211","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2551437525","https://openalex.org/W2802488037","https://openalex.org/W2887814324","https://openalex.org/W2901616798","https://openalex.org/W2946508582","https://openalex.org/W2947256846","https://openalex.org/W2972909277","https://openalex.org/W3044557466","https://openalex.org/W3096084197","https://openalex.org/W3141239769","https://openalex.org/W3151950999","https://openalex.org/W4236377898","https://openalex.org/W4292970115","https://openalex.org/W4293093798","https://openalex.org/W4313353807","https://openalex.org/W4318711056","https://openalex.org/W4388759395","https://openalex.org/W4391342318"],"related_works":["https://openalex.org/W4382289151","https://openalex.org/W3097523643","https://openalex.org/W3200601537","https://openalex.org/W4293093798","https://openalex.org/W4389980393","https://openalex.org/W2887814324","https://openalex.org/W4402391057","https://openalex.org/W4386549186","https://openalex.org/W3014419828","https://openalex.org/W7160784731"],"abstract_inverted_index":{"Advancements":[0],"in":[1,15],"machine":[2],"learning":[3,6],"and":[4,12,40,122],"deep":[5],"benefit":[7],"access":[8],"control":[9],"systems,":[10],"forensics,":[11],"biometrics":[13],"particularly":[14],"speaker":[16,31,83,136],"identification":[17,137],"systems.":[18],"The":[19,95,125],"SincNet":[20,80],"architecture":[21],"is":[22,89,98],"a":[23,57,59,86],"distinct":[24],"convolutional":[25,46],"neural":[26],"network":[27,117],"(CNN)":[28],"designed":[29],"for":[30,81],"identification.":[32,84],"It":[33],"operates":[34],"by":[35,142,149],"taking":[36],"one-dimensional":[37],"raw":[38],"speech":[39],"directing":[41],"it":[42],"through":[43],"its":[44],"initial":[45],"layer,":[47],"consisting":[48],"of":[49,77,109,112,127],"Sinc":[50],"filters.":[51],"In":[52],"this":[53],"work,":[54],"we":[55,73],"present":[56],"SincsquareNet,":[58,135],"CNN":[60],"that":[61],"efficiently":[62],"learns":[63],"customized":[64],"triangular":[65],"band-pass":[66],"filters":[67],"using":[68],"trainable":[69],"Sinc-squared":[70],"functions.":[71],"Also,":[72],"propose":[74],"the":[75,102,110,116,128],"fusion":[76],"SincsqaureNet":[78],"with":[79],"robust":[82,120],"Further,":[85],"self-attention":[87],"mechanism":[88],"employed":[90],"to":[91,100,134],"obtain":[92],"discriminating":[93],"features.":[94],"Librispeech":[96],"dataset":[97],"used":[99],"validate":[101],"proposed":[103],"framework.":[104],"This":[105],"approach":[106],"makes":[107],"use":[108],"best":[111],"both":[113],"filters,":[114],"helps":[115],"learn":[118],"more":[119],"features,":[121],"converges":[123],"faster.":[124],"findings":[126],"experiments":[129],"show":[130],"that,":[131],"when":[132],"compared":[133],"accuracy":[138],"was":[139,147],"relatively":[140],"improved":[141],"8%,":[143],"while":[144],"validation":[145],"loss":[146],"reduced":[148],"7%.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-04-09T00:00:00"}