{"id":"https://openalex.org/W7139105751","doi":"https://doi.org/10.1109/lsp.2026.3675922","title":"Bin-Wise Zone-Based Speech Presence Detection With Metric-Aligned DCF Optimization","display_name":"Bin-Wise Zone-Based Speech Presence Detection With Metric-Aligned DCF Optimization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139105751","doi":"https://doi.org/10.1109/lsp.2026.3675922"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3675922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3675922","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5129932347","display_name":"Doyeon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Doyeon Kim","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0008-1055-0563","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111441929","display_name":"Sung Kyo Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092488","display_name":"Custodix (Belgium)","ror":"https://ror.org/00m6eb133","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210092488"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Sung Kyo Jung","raw_affiliation_strings":["Audio BU, Goodix Technology, Leuven, Belgium"],"raw_orcid":"https://orcid.org/0009-0002-0724-5871","affiliations":[{"raw_affiliation_string":"Audio BU, Goodix Technology, Leuven, Belgium","institution_ids":["https://openalex.org/I4210092488"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35883449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1471","last_page":"1475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.993399977684021,"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":0.993399977684021,"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":0.002400000113993883,"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/T11448","display_name":"Face recognition and analysis","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5227000117301941},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49970000982284546},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.49869999289512634},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42660000920295715},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3824999928474426},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.37779998779296875},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.373199999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633000016212463},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49869999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43149998784065247},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.37779998779296875},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.373199999332428},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2542000114917755},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3675922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3675922","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6572275757789612}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,94],"paper,":[2],"we":[3,51],"study":[4],"zone-based":[5],"speech":[6,148],"presence":[7],"detection":[8,28,44,60,72,149],"for":[9,82,146],"a":[10,16,33,53,58,97],"spatially":[11],"constrained":[12],"target":[13],"located":[14],"within":[15],"fixed":[17],"\u00b130\u00b0":[18],"frontal":[19],"region":[20],"in":[21,73],"reverberant,":[22],"noisy,":[23],"and":[24,38,78,84,119],"multi-speaker":[25],"environments.":[26],"Conventional":[27],"methods":[29],"often":[30],"suffer":[31],"from":[32],"misalignment":[34],"between":[35],"training":[36,90],"objectives":[37],"operational":[39],"metrics":[40],"like":[41],"the":[42,68,74,89,112,123],"minimum":[43],"cost":[45,61],"function":[46,62],"(minDCF).":[47],"To":[48],"resolve":[49],"this,":[50],"propose":[52],"metric-aligned":[54],"optimization":[55],"framework":[56],"using":[57,96],"differentiable":[59],"(aDCF)":[63],"loss.":[64],"This":[65,129],"approach":[66],"formulates":[67],"task":[69],"as":[70],"bin-wise":[71],"complex":[75],"spectral":[76],"domain":[77],"embeds":[79],"asymmetric":[80],"costs":[81],"misses":[83],"false":[85],"alarms":[86],"directly":[87],"into":[88],"objective.":[91],"We":[92],"evaluate":[93],"method":[95],"standard":[98,109],"Convolutional":[99],"Recurrent":[100],"Neural":[101],"Network":[102],"(CRNN).":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"that":[107,131],"replacing":[108],"losses":[110],"with":[111],"proposed":[113],"aDCF":[114],"loss":[115,139],"consistently":[116],"improves":[117],"minDCF":[118],"F1-score":[120],"without":[121],"changing":[122],"model":[124],"architecture":[125],"or":[126],"inference":[127],"procedure.":[128],"confirms":[130],"significant":[132],"performance":[133],"gains":[134],"can":[135],"be":[136],"achieved":[137],"through":[138],"design":[140],"alone,":[141],"offering":[142],"an":[143],"efficient":[144],"solution":[145],"two-microphone":[147],"systems.":[150]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-20T00:00:00"}