{"id":"https://openalex.org/W3119975802","doi":"https://doi.org/10.1109/siu49456.2020.9302177","title":"Speech Activity Detection Under Adverse Conditions Using Neural Networks and Speaker Diarization","display_name":"Speech Activity Detection Under Adverse Conditions Using Neural Networks and Speaker Diarization","publication_year":2020,"publication_date":"2020-10-05","ids":{"openalex":"https://openalex.org/W3119975802","doi":"https://doi.org/10.1109/siu49456.2020.9302177","mag":"3119975802"},"language":"en","primary_location":{"id":"doi:10.1109/siu49456.2020.9302177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu49456.2020.9302177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","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/A5018311726","display_name":"\u0130smail Rasim \u00dclgen","orcid":"https://orcid.org/0000-0003-4593-9057"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"\u0130smail Rasim \u00dclgen","raw_affiliation_strings":["Boğaziçi Üniversitesi,Elektrik-Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc"],"affiliations":[{"raw_affiliation_string":"Boğaziçi Üniversitesi,Elektrik-Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murat Sara\u00e7lar","raw_affiliation_strings":["Boğaziçi Üniversitesi,Elektrik-Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc"],"affiliations":[{"raw_affiliation_string":"Boğaziçi Üniversitesi,Elektrik-Elektronik M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018311726"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17070441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9980000257492065,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7843512892723083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7781643867492676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7655916213989258},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7105259299278259},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5854106545448303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5740158557891846},{"id":"https://openalex.org/keywords/activity-detection","display_name":"Activity detection","score":0.5328987240791321},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5074431300163269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46107056736946106},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4287925064563751},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4238669276237488},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.411374568939209},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3384043872356415}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7843512892723083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781643867492676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7655916213989258},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7105259299278259},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5854106545448303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5740158557891846},{"id":"https://openalex.org/C2988656282","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity detection","level":2,"score":0.5328987240791321},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5074431300163269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46107056736946106},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4287925064563751},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4238669276237488},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.411374568939209},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3384043872356415},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu49456.2020.9302177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu49456.2020.9302177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2048497537","https://openalex.org/W2096702961","https://openalex.org/W2129120544","https://openalex.org/W2149053750","https://openalex.org/W2890964092"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W1521299571","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W2144470400","https://openalex.org/W3119975802"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"a":[3,12,17,49,79,85,96],"robust":[4,97],"speech":[5,59,74,87,106],"activity":[6,60,75,88,107],"detection":[7,76,89,108],"(SAD)":[8],"system":[9,90,94],"consisting":[10],"of":[11,30],"neural":[13,50],"network":[14,51],"classifier":[15,52],"and":[16,46,83],"speaker":[18,68],"diarization":[19,69],"module":[20],"that":[21,67],"works":[22],"under":[23,36],"noisy":[24,37],"conditions":[25],"is":[26,65,91],"designed.":[27,92],"The":[28,93],"performance":[29,98],"baseline":[31,44,105],"SAD":[32],"systems":[33,109],"degrades":[34],"significantly":[35],"conditions.":[38],"Under":[39],"these":[40],"conditions,":[41],"rather":[42],"than":[43],"features":[45,56],"classification":[47],"methods,":[48],"using":[53],"more":[54,61,80],"advanced":[55],"can":[57,70],"detect":[58],"successfully.":[62],"Besides,":[63],"it":[64],"seen":[66],"be":[71],"used":[72],"in":[73,78,99,103],"problem":[77],"advantageous":[81],"way,":[82],"finally":[84],"two-stage":[86],"has":[95],"real-life":[100],"office":[101],"recordings":[102],"which":[104],"perform":[110],"poorly.":[111]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}