{"id":"https://openalex.org/W4405709427","doi":"https://doi.org/10.1109/iscslp63861.2024.10800177","title":"LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification","display_name":"LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709427","doi":"https://doi.org/10.1109/iscslp63861.2024.10800177"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5089332230","display_name":"Shuanghong Liu","orcid":"https://orcid.org/0009-0007-8597-2229"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuanghong Liu","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020817636","display_name":"Zhida Song","orcid":"https://orcid.org/0000-0002-4987-5962"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhida Song","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000449705","display_name":"Zhihua Fang","orcid":"https://orcid.org/0000-0002-3018-7414"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Fang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067399917","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-2218-005X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Urumqi"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Urumqi","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089332230"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70216043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9731000065803528,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9196000099182129,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6360812187194824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6360812187194824}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2006712587","https://openalex.org/W2041823554","https://openalex.org/W2107638917","https://openalex.org/W2117671523","https://openalex.org/W2150769028","https://openalex.org/W2165880886","https://openalex.org/W2531409750","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2963420686","https://openalex.org/W2981087920","https://openalex.org/W3024869864","https://openalex.org/W3166898278","https://openalex.org/W4221154745","https://openalex.org/W4372271885","https://openalex.org/W4372340947","https://openalex.org/W4385822752","https://openalex.org/W4385823321","https://openalex.org/W4385823498","https://openalex.org/W4386071462","https://openalex.org/W4392904114","https://openalex.org/W4395046164","https://openalex.org/W6604254268","https://openalex.org/W6638667902","https://openalex.org/W6726497184"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Due":[0],"to":[1,24,40,53,66,99,130,150,190],"its":[2],"superior":[3],"performance":[4],"and":[5,119,134,146,156,180,202],"fewer":[6],"parameters,":[7,80],"CAM++":[8,72,129],"has":[9,74],"become":[10],"the":[11,45,54,101,105,111,125,136,152,162,168,186,191,196,203,210],"state-of-the-art":[12],"model":[13,19,112,151,170,174,193,211],"for":[14,85],"speaker":[15],"verification":[16],"tasks.":[17],"This":[18],"uses":[20],"2D":[21,49],"convolutional":[22],"blocks":[23],"extract":[25,41],"front-end":[26],"features,":[27,62],"which":[28,63],"are":[29,213],"then":[30],"fed":[31],"into":[32],"a":[33,57,75,181],"densely":[34],"connected":[35],"time-delay":[36],"neural":[37],"network":[38,107],"backbone":[39],"deep":[42],"features.":[43],"However,":[44],"simple":[46],"stacking":[47],"of":[48,56,60,79,108,128,178,183],"convolutions":[50,98,103],"may":[51],"lead":[52],"generation":[55],"significant":[58],"amount":[59],"redundant":[61,132],"is":[64,82,198,205],"detrimental":[65],"efficient":[67],"feature":[68,137],"extraction.":[69],"Furthermore,":[70],"although":[71],"already":[73],"relatively":[76],"small":[77],"number":[78],"there":[81],"still":[83],"room":[84],"further":[86,160],"optimization.":[87],"To":[88],"address":[89],"these":[90],"issues,":[91],"this":[92],"paper":[93],"first":[94],"employs":[95],"depthwise":[96],"separable":[97],"replace":[100],"dilated":[102],"in":[104,124],"back-end":[106],"CAM++,":[109],"making":[110],"more":[113],"lightweight.":[114],"Next,":[115],"we":[116,143],"introduce":[117],"spatial":[118],"channel":[120],"reconstruction":[121],"convolution":[122],"(SCConv)":[123],"ResBlock":[126],"module":[127],"reduce":[131],"features":[133],"optimize":[135],"extraction":[138],"process.":[139],"Finally,":[140],"after":[141],"SCConv,":[142],"apply":[144],"squeeze":[145],"excitation":[147],"attention":[148],"mechanism":[149],"interdependencies":[153],"between":[154],"channels":[155],"recalibrate":[157],"each":[158],"channel,":[159],"enhancing":[161],"model's":[163],"representational":[164],"capacity.":[165],"We":[166],"name":[167],"resulting":[169],"LE-CAM++.":[171],"Our":[172],"proposed":[173],"achieves":[175],"an":[176],"EER":[177,197],"0.686":[179],"minDCF":[182,204],"0.084":[184],"on":[185],"VoxCeleb1\u2013O":[187],"dataset.":[188],"Compared":[189],"baseline":[192],"CAM":[194],"++,":[195],"reduced":[199,206,214],"by":[200,207,215],"11%,":[201],"28%.":[208],"Additionally,":[209],"parameters":[212],"8%.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}