{"id":"https://openalex.org/W2071301891","doi":"https://doi.org/10.1109/cidm.2013.6597233","title":"Unsupervised multimodal VAD using sequential hierarchy","display_name":"Unsupervised multimodal VAD using sequential hierarchy","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2071301891","doi":"https://doi.org/10.1109/cidm.2013.6597233","mag":"2071301891"},"language":"en","primary_location":{"id":"doi:10.1109/cidm.2013.6597233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2013.6597233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","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/A5112702870","display_name":"Rameez Ahmad","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rameez Ahmad","raw_affiliation_strings":["Information Systems, Security and Forensics (ISSF) Laboratory, University of Michigan-Dearborn, Dearborn, MI, USA","Inf. Syst., Security & Forensics (ISSF) Lab., Univ. of Michigan, Dearborn, MI, USA"],"affiliations":[{"raw_affiliation_string":"Information Systems, Security and Forensics (ISSF) Laboratory, University of Michigan-Dearborn, Dearborn, MI, USA","institution_ids":["https://openalex.org/I4210130704"]},{"raw_affiliation_string":"Inf. Syst., Security & Forensics (ISSF) Lab., Univ. of Michigan, Dearborn, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066568195","display_name":"Syed Paymaan Raza","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Paymaan Raza","raw_affiliation_strings":["Information Systems, Security and Forensics (ISSF) Laboratory, University of Michigan-Dearborn, Dearborn, MI, USA","Inf. Syst., Security & Forensics (ISSF) Lab., Univ. of Michigan, Dearborn, MI, USA"],"affiliations":[{"raw_affiliation_string":"Information Systems, Security and Forensics (ISSF) Laboratory, University of Michigan-Dearborn, Dearborn, MI, USA","institution_ids":["https://openalex.org/I4210130704"]},{"raw_affiliation_string":"Inf. Syst., Security & Forensics (ISSF) Lab., Univ. of Michigan, Dearborn, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033599238","display_name":"Hafiz Malik","orcid":"https://orcid.org/0000-0001-6006-3888"},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hafiz Malik","raw_affiliation_strings":["Information Systems, Security and Forensics (ISSF) Laboratory, University of Michigan-Dearborn, Dearborn, MI, USA","Inf. Syst., Security & Forensics (ISSF) Lab., Univ. of Michigan, Dearborn, MI, USA"],"affiliations":[{"raw_affiliation_string":"Information Systems, Security and Forensics (ISSF) Laboratory, University of Michigan-Dearborn, Dearborn, MI, USA","institution_ids":["https://openalex.org/I4210130704"]},{"raw_affiliation_string":"Inf. Syst., Security & Forensics (ISSF) Lab., Univ. of Michigan, Dearborn, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112702870"],"corresponding_institution_ids":["https://openalex.org/I27837315","https://openalex.org/I4210130704"],"apc_list":null,"apc_paid":null,"fwci":0.6384,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69175354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"177"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8060714602470398},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7201113700866699},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6898290514945984},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6809799671173096},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5619600415229797},{"id":"https://openalex.org/keywords/alarm","display_name":"ALARM","score":0.5013306140899658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4669327139854431},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.45401373505592346},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3202759027481079},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1318906843662262},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0722789466381073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060714602470398},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7201113700866699},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6898290514945984},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6809799671173096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5619600415229797},{"id":"https://openalex.org/C2779119184","wikidata":"https://www.wikidata.org/wiki/Q294350","display_name":"ALARM","level":2,"score":0.5013306140899658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4669327139854431},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.45401373505592346},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3202759027481079},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1318906843662262},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0722789466381073},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cidm.2013.6597233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2013.6597233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1973067693","https://openalex.org/W2116529913","https://openalex.org/W2142170306","https://openalex.org/W2198815242","https://openalex.org/W2400967734","https://openalex.org/W3145319331","https://openalex.org/W3147588286","https://openalex.org/W6677131165"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"In":[0,40,72],"speech":[1],"processing":[2],"systems,":[3],"the":[4,7,16],"performance":[5,102],"of":[6,31,83,103],"Voice":[8],"Activity":[9],"Detector":[10],"(VAD)":[11],"is":[12,34],"a":[13,45,80,88],"bottleneck":[14],"to":[15,36,69,74,86],"whole":[17],"system.":[18],"Traditional":[19],"VADs":[20],"are":[21,60],"solely":[22],"based":[23,48],"on":[24,49],"acoustic":[25],"features.":[26],"Additional":[27],"modality":[28],"in":[29],"form":[30],"visual":[32],"information":[33],"used":[35],"make":[37],"robust":[38],"VADs.":[39],"this":[41,76],"paper,":[42],"we":[43,78],"propose":[44],"multimodal":[46,89],"VAD":[47,56,106],"decision":[50,58],"fusion":[51],"between":[52],"two":[53],"modalities.":[54,71],"Visual":[55],"(VVAD)":[57],"vectors":[59],"interpolated":[61],"so":[62],"that":[63],"logical":[64],"operators":[65],"can":[66],"be":[67],"applied":[68],"both":[70,84],"order":[73],"avoid":[75],"interpolation,":[77],"suggest":[79],"sequential":[81],"arrangement":[82],"subsystems":[85],"achieve":[87],"VAD.":[90],"The":[91],"proposed":[92],"method":[93],"considerably":[94],"reduces":[95],"false":[96],"alarm":[97],"rates":[98],"when":[99],"compared":[100],"with":[101],"standalone":[104],"audio":[105],"(AVAD).":[107]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
