{"id":"https://openalex.org/W4392902754","doi":"https://doi.org/10.1109/icassp48485.2024.10446174","title":"Gradient Weighting for Speaker Verification in Extremely Low Signal-to-Noise Ratio","display_name":"Gradient Weighting for Speaker Verification in Extremely Low Signal-to-Noise Ratio","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902754","doi":"https://doi.org/10.1109/icassp48485.2024.10446174"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5116252196","display_name":"Yi Ma","orcid":"https://orcid.org/0009-0008-5473-5498"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yi Ma","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Hautam\u00e4ki","raw_affiliation_strings":["University of Eastern Finland,School of Computing,Finland","School of Computing, University of Eastern Finland, Finland"],"affiliations":[{"raw_affiliation_string":"University of Eastern Finland,School of Computing,Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]},{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007002715","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0002-3468-6149"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China","School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","Shenzhen Research Institute of Big Data, Shenzhen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5116252196"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.0127,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7859844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11311","last_page":"11315"},"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":0.9997000098228455,"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":0.995199978351593,"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/weighting","display_name":"Weighting","score":0.7667093276977539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401800155639648},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7356837391853333},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.7197580933570862},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6708369851112366},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5793718099594116},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5678504705429077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5438154935836792},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4859522581100464},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4704686105251312},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4331589341163635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36710721254348755},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.26980912685394287},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19996139407157898},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13849160075187683},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08611300587654114},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.052039116621017456}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7667093276977539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401800155639648},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7356837391853333},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.7197580933570862},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6708369851112366},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5793718099594116},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5678504705429077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5438154935836792},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4859522581100464},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4704686105251312},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4331589341163635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36710721254348755},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26980912685394287},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19996139407157898},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13849160075187683},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08611300587654114},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.052039116621017456},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6809183074","display_name":null,"funder_award_id":"Project No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G766701999","display_name":null,"funder_award_id":"20220002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2219249508","https://openalex.org/W2617258110","https://openalex.org/W2808631503","https://openalex.org/W2962858109","https://openalex.org/W2963715038","https://openalex.org/W2972404066","https://openalex.org/W2972425344","https://openalex.org/W2982037672","https://openalex.org/W3024301174","https://openalex.org/W3097906045","https://openalex.org/W3161158930","https://openalex.org/W3176482836","https://openalex.org/W3196650842","https://openalex.org/W4221154746","https://openalex.org/W4223587462","https://openalex.org/W4225682608","https://openalex.org/W4283703262","https://openalex.org/W4288055783","https://openalex.org/W4307929719","https://openalex.org/W4372340947","https://openalex.org/W4375869169","https://openalex.org/W4377371819","https://openalex.org/W4385822426","https://openalex.org/W4385822943","https://openalex.org/W4402778510","https://openalex.org/W6688816777","https://openalex.org/W6734194636","https://openalex.org/W6738549535","https://openalex.org/W6779361924","https://openalex.org/W6841262489","https://openalex.org/W6846302668","https://openalex.org/W6847215460","https://openalex.org/W6852962002","https://openalex.org/W6857495872","https://openalex.org/W6859383537"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W1998549096","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W4375869276","https://openalex.org/W3002068412","https://openalex.org/W1585241115"],"abstract_inverted_index":{"Speaker":[0],"verification":[1,135],"is":[2,18,51,67],"hampered":[3],"by":[4,109],"background":[5],"noise,":[6,132],"particularly":[7],"at":[8],"extremely":[9],"low":[10],"Signal-to-Noise":[11],"Ratio":[12],"(SNR)":[13],"under":[14],"0":[15],"dB.":[16],"It":[17],"difficult":[19],"to":[20],"suppress":[21],"noise":[22,46,94],"without":[23],"introducing":[24],"unwanted":[25],"artifacts,":[26],"which":[27,40,60],"adversely":[28],"affects":[29],"speaker":[30,74,120,134],"verification.":[31,121],"We":[32,106],"proposed":[33],"the":[34,54,57,63,65,73,81,87,116],"mechanism":[35,50],"called":[36],"Gradient":[37],"Weighting":[38],"(Grad-W),":[39],"dynamically":[41],"identifies":[42],"and":[43,95,114],"reduces":[44,130],"artifact":[45,93,131],"during":[47,102],"prediction.":[48],"The":[49,122],"based":[52],"on":[53,77,86,119],"property":[55],"that":[56,126],"gradient":[58],"indicates":[59],"parts":[61],"of":[62,104],"input":[64],"model":[66,113],"paying":[68],"attention":[69],"to.":[70],"Specifically,":[71],"when":[72],"network":[75],"focuses":[76],"a":[78],"region":[79,101],"in":[80],"denoised":[82],"utterance":[83,118],"but":[84],"not":[85],"clean":[88],"counterpart,":[89],"we":[90],"consider":[91],"it":[92,108],"assign":[96],"higher":[97],"weights":[98],"for":[99],"this":[100],"optimization":[103],"enhancement.":[105],"validate":[107],"training":[110],"an":[111],"enhancement":[112],"testing":[115],"enhanced":[117],"experimental":[123],"results":[124],"show":[125],"our":[127],"approach":[128],"effectively":[129],"improving":[133],"across":[136],"various":[137],"SNR":[138],"levels.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}