{"id":"https://openalex.org/W3135733472","doi":"https://doi.org/10.1109/iscslp49672.2021.9362108","title":"Channel Interdependence Enhanced Speaker Embeddings for Far-Field Speaker Verification","display_name":"Channel Interdependence Enhanced Speaker Embeddings for Far-Field Speaker Verification","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3135733472","doi":"https://doi.org/10.1109/iscslp49672.2021.9362108","mag":"3135733472"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107107/1/Zhao_Channel_Interdependence_Enhanced.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009225924","display_name":"Lingjun Zhao","orcid":"https://orcid.org/0000-0003-2369-8862"},"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":true,"raw_author_name":"Ling-jun Zhao","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"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":"Man-Wai Mak","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009225924"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.7717,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69650378,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9937000274658203,"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":0.7546219825744629},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6497249007225037},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6202941536903381},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.57331383228302},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5373173952102661},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4943387508392334},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.48590579628944397},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4687870740890503},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4634515941143036},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4625854194164276},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.4114949107170105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4110490083694458},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3460540771484375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3211915194988251},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2178547978401184},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.09556740522384644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09156429767608643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7546219825744629},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6497249007225037},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6202941536903381},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.57331383228302},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5373173952102661},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4943387508392334},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.48590579628944397},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4687870740890503},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4634515941143036},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4625854194164276},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.4114949107170105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4110490083694458},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3460540771484375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3211915194988251},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2178547978401184},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.09556740522384644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09156429767608643},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/107107","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107107","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107107/1/Zhao_Channel_Interdependence_Enhanced.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/107107","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107107","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107107/1/Zhao_Channel_Interdependence_Enhanced.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5400000214576721,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1023919524","display_name":null,"funder_award_id":", Grant","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/G2168692635","display_name":null,"funder_award_id":"61971371","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/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/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/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/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135733472.pdf","grobid_xml":"https://content.openalex.org/works/W3135733472.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W2053150333","https://openalex.org/W2164502538","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2516764878","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2796485741","https://openalex.org/W2808631503","https://openalex.org/W2888897023","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916024349","https://openalex.org/W2928165649","https://openalex.org/W2949526695","https://openalex.org/W2963040451","https://openalex.org/W2963420686","https://openalex.org/W2963446712","https://openalex.org/W2963576203","https://openalex.org/W2972311940","https://openalex.org/W2972369255","https://openalex.org/W2972386477","https://openalex.org/W2972961496","https://openalex.org/W2973147881","https://openalex.org/W3015231328","https://openalex.org/W3015368919","https://openalex.org/W3016143998","https://openalex.org/W3024200162","https://openalex.org/W3024869864","https://openalex.org/W3025515949","https://openalex.org/W3103152812","https://openalex.org/W4288558760","https://openalex.org/W6688816777","https://openalex.org/W6725739302","https://openalex.org/W6743731764","https://openalex.org/W6760112457","https://openalex.org/W6773971935","https://openalex.org/W6777437564"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Recognizing":[0],"speakers":[1],"from":[2],"a":[3,124,135,150],"distance":[4],"using":[5],"far-field":[6],"microphones":[7],"is":[8,101],"difficult":[9],"because":[10],"of":[11,33,130,153],"the":[12,27,39,53,56,65,70,79,84,107,115,146,163],"environmental":[13],"noise":[14],"and":[15,30,68,105,117,158],"reverberation":[16],"distortion.":[17],"In":[18],"this":[19],"work,":[20],"we":[21,37,58,122],"tackle":[22],"these":[23,75,131],"problems":[24],"by":[25],"strengthening":[26],"frame-level":[28,49],"processing":[29],"feature":[31,99,120],"aggregation":[32,100],"x-vector":[34],"networks.":[35],"Specifically,":[36],"restructure":[38],"dilated":[40],"convolutional":[41],"layers":[42,87],"into":[43],"Res2Net":[44,80,141],"blocks":[45],"to":[46,63,73,103,134],"generate":[47],"multi-scale":[48],"features.":[50],"To":[51,112],"exploit":[52],"relationship":[54],"between":[55],"channels,":[57],"introduce":[59],"squeeze-and-excitation":[60],"(SE)":[61],"units":[62,77],"rescale":[64],"channels'":[66],"activations":[67],"investigate":[69],"best":[71],"places":[72],"put":[74],"SE":[76],"in":[78,156,160],"blocks.":[81],"Based":[82],"on":[83,162],"hypothesis":[85],"that":[86,145],"at":[88,94,109],"different":[89,95],"depth":[90],"contain":[91],"speaker":[92],"information":[93],"granularity":[96],"levels,":[97],"multi-block":[98],"introduced":[102],"propagate":[104],"aggregate":[106],"features":[108],"various":[110],"depths.":[111],"optimally":[113],"weight":[114],"channels":[116],"frames":[118],"during":[119],"aggregation,":[121],"propose":[123],"channel-dependent":[125],"attention":[126],"mechanism.":[127],"Combining":[128],"all":[129],"enhancements":[132],"leads":[133],"network":[136,148],"architecture":[137],"called":[138],"channel-interdependence":[139],"enhanced":[140],"(CE-Res2Net).":[142],"Results":[143],"show":[144],"proposed":[147],"achieves":[149],"relative":[151],"improvement":[152],"about":[154],"16%":[155],"EER":[157],"17%":[159],"minDCF":[161],"VOiCES":[164],"2019":[165],"Challenge's":[166],"evaluation":[167],"set.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}