{"id":"https://openalex.org/W4387068218","doi":"https://doi.org/10.1109/lsp.2023.3319229","title":"DeepComboSAD: Spectro-Temporal Correlation Based Speech Activity Detection for Naturalistic Audio Streams","display_name":"DeepComboSAD: Spectro-Temporal Correlation Based Speech Activity Detection for Naturalistic Audio Streams","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387068218","doi":"https://doi.org/10.1109/lsp.2023.3319229"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3319229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3319229","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/A5088979748","display_name":"Aditya Joglekar","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aditya Joglekar","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","CRSS: Center for Robust Speech Systems, University of Texas at Dallas, Richardson, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","CRSS: Center for Robust Speech Systems, University of Texas at Dallas, Richardson, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"CRSS: Center for Robust Speech Systems, University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088979748"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.225,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80175274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"1472","last_page":"1476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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":0.9962000250816345,"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":0.9941999912261963,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9269000291824341,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8292872905731201},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7461420297622681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7258420586585999},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4791966378688812},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46393540501594543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46321162581443787},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4425482749938965},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.431831032037735},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38666146993637085},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.30677828192710876},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.090340256690979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292872905731201},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7461420297622681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7258420586585999},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4791966378688812},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46393540501594543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46321162581443787},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4425482749938965},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.431831032037735},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38666146993637085},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.30677828192710876},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.090340256690979},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3319229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3319229","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/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327708","display_name":"University of Texas at Dallas","ror":"https://ror.org/049emcs32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1580555281","https://openalex.org/W1604034532","https://openalex.org/W2023582935","https://openalex.org/W2028706510","https://openalex.org/W2048497537","https://openalex.org/W2120480179","https://openalex.org/W2129120544","https://openalex.org/W2149053750","https://openalex.org/W2152395643","https://openalex.org/W2157363431","https://openalex.org/W2170644918","https://openalex.org/W2182389375","https://openalex.org/W2746626166","https://openalex.org/W2767895109","https://openalex.org/W2791616807","https://openalex.org/W2805399811","https://openalex.org/W2889029201","https://openalex.org/W2889041236","https://openalex.org/W2892300106","https://openalex.org/W2936774411","https://openalex.org/W2954930777","https://openalex.org/W2969937074","https://openalex.org/W2972869740","https://openalex.org/W2995588677","https://openalex.org/W3007258144","https://openalex.org/W3095913803","https://openalex.org/W3097636940","https://openalex.org/W3196635633","https://openalex.org/W3197179619","https://openalex.org/W3197479203","https://openalex.org/W3198793808","https://openalex.org/W3214515055","https://openalex.org/W4214921663","https://openalex.org/W4319862673","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6767351229","https://openalex.org/W6945080101"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Speech":[0,13],"activity":[1],"detection":[2],"(SAD)":[3],"serves":[4],"as":[5,20],"a":[6,98,121,157,166],"crucial":[7],"front-end":[8],"system":[9,116,136],"to":[10,41,65,85,88,125,127,162,178],"several":[11],"downstream":[12],"and":[14,27,48,69,133,139,183],"Language":[15],"Technology":[16],"(SLT)":[17],"tasks":[18],"such":[19],"speaker":[21,24],"diarization":[22],"(SD),":[23],"identification":[25],"(SID),":[26],"speech":[28],"recognition":[29],"(ASR).":[30],"Recent":[31],"years":[32],"have":[33],"seen":[34],"deep":[35,81],"learning":[36,82],"(DL)-based":[37],"SAD":[38,52,100,186],"systems":[39,198],"designed":[40,84],"improve":[42],"robustness":[43],"against":[44],"static":[45],"background":[46],"noise":[47,90],"interfering":[49],"speakers.":[50],"However,":[51],"performance":[53,172],"can":[54],"be":[55,86],"severely":[56],"limited":[57],"for":[58,102],"conversations":[59],"recorded":[60],"in":[61,93,213],"naturalistic":[62,94],"environments":[63],"due":[64],"dynamic":[66],"acoustic":[67,128],"scenarios":[68],"previously":[70],"unseen":[71],"nonspeech":[72],"artifacts.":[73],"In":[74],"this":[75],"study,":[76],"we":[77],"propose":[78],"an":[79],"end-to-end":[80],"framework":[83],"robust":[87],"time-varying":[89],"profiles":[91],"observed":[92],"audio.":[95],"We":[96],"develop":[97],"novel":[99],"solution":[101],"the":[103,142,151,179,193,205,208,214],"UTDallas":[104],"Fearless":[105,143],"Steps":[106,144],"Apollo":[107,112,152],"Corpus":[108],"based":[109],"on":[110,141],"NASA's":[111],"missions.":[113,134],"The":[114,188],"proposed":[115,189],"leverages":[117],"spectrotemporal":[118],"correlations":[119],"with":[120],"threshold":[122],"optimization":[123],"mechanism":[124],"adjust":[126],"variabilities":[129],"across":[130],"multiple":[131],"channels":[132],"This":[135],"is":[137],"trained":[138],"evaluated":[140],"Challenge":[145],"(FSC)":[146],"corpus":[147],"(a":[148],"subset":[149],"of":[150,160,174,207],"corpus).":[153],"Experimental":[154],"results":[155],"indicate":[156],"high":[158],"degree":[159],"adaptability":[161],"out-of-domain":[163],"data,":[164],"achieving":[165],"relative":[167],"Detection":[168],"Cost":[169],"Function":[170],"(DCF)":[171],"improvement":[173],"over":[175],"50%":[176],"compared":[177],"previous":[180],"FSC":[181,200],"baselines":[182],"state-of-the-art":[184],"(SOTA)":[185],"systems.":[187],"model":[190],"also":[191],"outperforms":[192],"most":[194],"recent":[195],"DL-based":[196],"SOTA":[197],"from":[199],"Phase-4.":[201],"Ablation":[202],"analysis":[203],"validates":[204],"effectiveness":[206],"combined":[209],"spectro-temporal":[210],"features":[211],"computed":[212],"DeepComboSAD":[215],"network.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}