{"id":"https://openalex.org/W4372260481","doi":"https://doi.org/10.1109/icassp49357.2023.10095415","title":"Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification","display_name":"Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260481","doi":"https://doi.org/10.1109/icassp49357.2023.10095415"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101527946","display_name":"Jingyu Li","orcid":"https://orcid.org/0000-0002-1163-4557"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyu Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002748018","display_name":"Yusheng Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusheng Tian","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101527946"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.9231,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88403614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9983000159263611,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.785042405128479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821518182754517},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7567943334579468},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7044544219970703},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6568857431411743},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5603708028793335},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5533053874969482},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4699585437774658},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46213001012802124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4024297297000885},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33157891035079956},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2797837257385254}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.785042405128479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821518182754517},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7567943334579468},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7044544219970703},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6568857431411743},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5603708028793335},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5533053874969482},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4699585437774658},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46213001012802124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4024297297000885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33157891035079956},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2797837257385254},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1589137271","https://openalex.org/W1836465849","https://openalex.org/W1936725236","https://openalex.org/W2046056978","https://openalex.org/W2129244720","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2502312327","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2963420686","https://openalex.org/W2969985801","https://openalex.org/W2972552635","https://openalex.org/W2981087920","https://openalex.org/W3010893827","https://openalex.org/W3024869864","https://openalex.org/W3034552520","https://openalex.org/W3095476325","https://openalex.org/W3135006803","https://openalex.org/W3141035251","https://openalex.org/W3163505255","https://openalex.org/W4221154746","https://openalex.org/W4296068991","https://openalex.org/W6631190155","https://openalex.org/W6638667902"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W2964954556","https://openalex.org/W3019910406"],"abstract_inverted_index":{"Deep":[0],"convolutional":[1],"neural":[2],"networks":[3],"(CNNs)":[4],"have":[5],"been":[6],"applied":[7],"to":[8,24,74,88],"extracting":[9],"speaker":[10,16,94,107],"embeddings":[11],"with":[12,139],"significant":[13],"success":[14],"in":[15,27,53,123],"verification.":[17],"Incorporating":[18],"the":[19,29,46,54,85,90],"attention":[20,39,55,70,126,131],"mechanism":[21],"has":[22],"shown":[23],"be":[25],"effective":[26,122],"improving":[28],"model":[30,135,143],"performance.":[31],"This":[32,61],"paper":[33],"presents":[34],"an":[35],"efficient":[36],"two-dimensional":[37],"convolution-based":[38],"module,":[40],"namely":[41],"C2D-Att.":[42],"The":[43,80,96,116,133],"interaction":[44],"between":[45],"convolution":[47,59],"channel":[48,76],"and":[49,77,128,145],"frequency":[50],"is":[51,98,121],"involved":[52],"calculation":[56],"by":[57],"lightweight":[58],"layers.":[60],"requires":[62],"only":[63],"a":[64,101],"small":[65],"number":[66],"of":[67,104,142],"parameters.":[68],"Fine-grained":[69],"weights":[71,81],"are":[72,82,111],"produced":[73],"represent":[75],"frequency-specific":[78],"information.":[79],"imposed":[83],"on":[84,113],"input":[86],"features":[87],"improve":[89],"representation":[91],"ability":[92],"for":[93,106],"modeling.":[95],"C2D-Att":[97,120],"integrated":[99],"into":[100],"modified":[102],"version":[103],"ResNet":[105],"embedding":[108],"extraction.":[109],"Experiments":[110],"conducted":[112],"VoxCeleb":[114],"datasets.":[115],"results":[117],"show":[118],"that":[119],"generating":[124],"discriminative":[125],"maps":[127],"outperforms":[129],"other":[130],"methods.":[132],"proposed":[134],"shows":[136],"robust":[137],"performance":[138],"different":[140],"scales":[141],"size":[144],"achieves":[146],"state-of-the-art":[147],"results.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}