{"id":"https://openalex.org/W3094892544","doi":"https://doi.org/10.1109/taslp.2020.3036237","title":"Block-Based High Performance CNN Architectures for Frame-Level Overlapping Speech Detection","display_name":"Block-Based High Performance CNN Architectures for Frame-Level Overlapping Speech Detection","publication_year":2020,"publication_date":"2020-11-06","ids":{"openalex":"https://openalex.org/W3094892544","doi":"https://doi.org/10.1109/taslp.2020.3036237","mag":"3094892544"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3036237","doi":"https://doi.org/10.1109/taslp.2020.3036237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3036237","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"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/A5112853229","display_name":"Midia Yousefi","orcid":null,"observed_orcids":[]},"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":"Midia Yousefi","raw_affiliation_strings":["Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, The University of Texas at Dallas, Richardson, TX, 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","observed_orcids":["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, Erik Jonsson School of Engineering and Computer Science, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, Erik Jonsson School of Engineering and Computer Science, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":3.3392,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.93648204,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"28","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0006000000284984708,"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":0.0005000000237487257,"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/frame-level-classification","display_name":"frame-level classification","score":0.8339999914169312},{"id":"https://openalex.org/keywords/interference-resistance","display_name":"interference resistance","score":0.42399999499320984},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.6800000071525574},{"id":"https://openalex.org/keywords/spectral-magnitude","display_name":"spectral magnitude","score":0.7120000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258075714111328},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7441936731338501},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6279102563858032},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5081639289855957},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47443878650665283},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46383509039878845},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4577144682407379},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4417518079280853},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4408305585384369},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.432756245136261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41815733909606934},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41315779089927673},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38685280084609985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38084012269973755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3589848279953003},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07928353548049927},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3036237","doi":"https://doi.org/10.1109/taslp.2020.3036237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3036237","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1888406694","display_name":null,"funder_award_id":"# 2016725","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G653523863","display_name":null,"funder_award_id":"1918032","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320327708","display_name":"University of Texas at Dallas","ror":"https://ror.org/049emcs32"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1602032261","https://openalex.org/W1603689368","https://openalex.org/W1604358271","https://openalex.org/W1836465849","https://openalex.org/W1964797398","https://openalex.org/W1971168548","https://openalex.org/W1987292658","https://openalex.org/W1991139021","https://openalex.org/W1992259772","https://openalex.org/W2005671413","https://openalex.org/W2015143272","https://openalex.org/W2047527596","https://openalex.org/W2079362249","https://openalex.org/W2090056283","https://openalex.org/W2114537326","https://openalex.org/W2120256304","https://openalex.org/W2123861288","https://openalex.org/W2125336414","https://openalex.org/W2143169494","https://openalex.org/W2144763279","https://openalex.org/W2169264834","https://openalex.org/W2170160479","https://openalex.org/W2194775991","https://openalex.org/W2402428045","https://openalex.org/W2406713305","https://openalex.org/W2508092598","https://openalex.org/W2508974694","https://openalex.org/W2591682631","https://openalex.org/W2601064856","https://openalex.org/W2745338770","https://openalex.org/W2889145072","https://openalex.org/W2917174945","https://openalex.org/W2919115771","https://openalex.org/W2964350391","https://openalex.org/W2966215472","https://openalex.org/W3002785901","https://openalex.org/W4234117503","https://openalex.org/W6685035135"],"related_works":["https://openalex.org/W3002785901","https://openalex.org/W7127441738","https://openalex.org/W4402351868","https://openalex.org/W4205259838","https://openalex.org/W4391967905","https://openalex.org/W4413368546","https://openalex.org/W3143147094","https://openalex.org/W2968071640","https://openalex.org/W3207539720","https://openalex.org/W4417137575"],"abstract_inverted_index":{"Speech":[0,6],"technology":[1,63],"systems":[2,31],"such":[3],"as":[4,93,95],"Automatic":[5],"Recognition":[7],"(ASR),":[8],"speaker":[9,11],"diarization,":[10],"recognition,":[12],"and":[13,151,157,195],"speech":[14,52,62,87,166,186],"synthesis":[15],"have":[16],"advanced":[17],"significantly":[18],"by":[19,129],"the":[20,114,125,140,170,177,180,207,214],"emergence":[21],"of":[22,28,109,142,179],"deep":[23],"learning":[24],"techniques.":[25],"However,":[26],"none":[27],"these":[29],"voice-enabled":[30],"perform":[32],"well":[33],"in":[34,39,74,88,107,116,183,212],"natural":[35],"environmental":[36,132],"circumstances,":[37],"specifically":[38],"situations":[40],"where":[41,71],"one":[42],"or":[43,134],"more":[44],"potential":[45],"interfering":[46],"talkers":[47],"are":[48],"involved.":[49],"Therefore,":[50],"overlapping":[51,86,165,185],"detection":[53],"has":[54],"become":[55],"an":[56],"important":[57],"front-end":[58],"triage":[59],"step":[60],"for":[61,68],"applications.":[64],"This":[65],"is":[66,81,101,161],"crucial":[67],"large-scale":[69],"datasets":[70],"manual":[72],"labeling":[73],"not":[75],"possible.":[76],"A":[77],"block-based":[78],"CNN":[79],"architecture":[80,100],"proposed":[82,99,181],"to":[83,103,113],"address":[84],"modeling":[85],"audio":[89],"streams":[90],"with":[91,188],"frames":[92,187],"short":[94],"25":[96],"ms.":[97],"The":[98,173],"robust":[102],"both:":[104],"(i)":[105],"shifts":[106],"distribution":[108],"network":[110,117,208],"activations":[111],"due":[112],"change":[115],"parameters":[118],"during":[119],"training,":[120],"(ii)":[121],"local":[122],"variations":[123],"from":[124],"input":[126,144],"features":[127,145],"caused":[128],"feature":[130],"extraction,":[131],"noise,":[133],"room":[135],"interference.":[136],"We":[137],"also":[138],"investigate":[139],"effect":[141],"alternate":[143],"including":[146],"spectral":[147],"magnitude,":[148],"MFCC,":[149],"MFB,":[150],"pyknogram":[152],"on":[153,163,169,198],"both":[154],"computational":[155],"time":[156],"classification":[158,215],"performance.":[159],"Evaluation":[160],"performed":[162],"simulated":[164],"signals":[167],"based":[168],"GRID":[171],"corpus.":[172],"experimental":[174],"results":[175],"highlight":[176],"capability":[178],"system":[182],"detecting":[184],"90.5%":[189],"accuracy,":[190],"93.5%":[191],"precision,":[192],"92.7%":[193],"recall,":[194],"92.8%":[196],"Fscore":[197],"same":[199],"gender":[200,205],"overlapped":[201],"speech.":[202],"For":[203],"opposite":[204],"cases,":[206],"scores":[209],"exceed":[210],"95%":[211],"all":[213],"metrics.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":8}],"updated_date":"2026-10-21T09:56:26.102985","created_date":"2020-11-09T00:00:00"}