{"id":"https://openalex.org/W2400845926","doi":"https://doi.org/10.21437/interspeech.2015-444","title":"Complete-linkage clustering for voice activity detection in audio and visual speech","display_name":"Complete-linkage clustering for voice activity detection in audio and visual speech","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2400845926","doi":"https://doi.org/10.21437/interspeech.2015-444","mag":"2400845926"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/85160/40/Houman_Interspeech2015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012849807","display_name":"Houman Ghaemmaghami","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Houman Ghaemmaghami","raw_affiliation_strings":["Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072416824","display_name":"Shahram Kalantari","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shahram Kalantari","raw_affiliation_strings":["Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":["Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Science and Engineering Faculty, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012849807"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":2.8942,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92016541,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2292","last_page":"2296"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481906414031982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7393220663070679},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6894755363464355},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6450662016868591},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.6234825253486633},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5902188420295715},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3275567591190338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31598183512687683},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15793856978416443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481906414031982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7393220663070679},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6894755363464355},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6450662016868591},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6234825253486633},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5902188420295715},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3275567591190338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31598183512687683},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15793856978416443},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:85160","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/85160/40/Houman_Interspeech2015.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 16th Annual Conference of the International Speech Communication Association, Interspeech 2015","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:85160","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/85160/40/Houman_Interspeech2015.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 16th Annual Conference of the International Speech Communication Association, Interspeech 2015","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2400845926.pdf","grobid_xml":"https://content.openalex.org/works/W2400845926.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1072292725","https://openalex.org/W1506438021","https://openalex.org/W1506806321","https://openalex.org/W1986769338","https://openalex.org/W2010133108","https://openalex.org/W2015214296","https://openalex.org/W2017835752","https://openalex.org/W2070176749","https://openalex.org/W2090716422","https://openalex.org/W2115717467","https://openalex.org/W2129120544","https://openalex.org/W2138130935","https://openalex.org/W2140623944","https://openalex.org/W2140979961","https://openalex.org/W2145030715","https://openalex.org/W2146818968","https://openalex.org/W2156038773","https://openalex.org/W2162162446","https://openalex.org/W2338994564","https://openalex.org/W2397634864","https://openalex.org/W2977447808","https://openalex.org/W3007258144","https://openalex.org/W3151878189","https://openalex.org/W4239330706"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2103239478","https://openalex.org/W2552102772","https://openalex.org/W1510046822","https://openalex.org/W2052688117","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"We":[0,15,29,80,116],"propose":[1],"a":[2,35,59,141],"novel":[3],"technique":[4],"for":[5,50],"conducting":[6],"robust":[7],"voice":[8],"activity":[9],"detection":[10],"(VAD)":[11],"in":[12,100,136],"high-noise":[13],"recordings.":[14],"use":[16],"Gaussian":[17],"mixture":[18],"modeling":[19],"(GMM)":[20],"to":[21,44,57,67,93,121,129],"train":[22],"two":[23,46],"generic":[24],"models;":[25],"speech":[26,76],"and":[27,66,77,89,111],"non-speech.":[28],"then":[30,117],"score":[31],"smaller":[32],"segments":[33,65,74],"of":[34,41,64,72,84,98,125,133,144],"given":[36],"(unseen)":[37],"recording":[38],"against":[39,87],"each":[40,51],"these":[42,145],"GMMs":[43],"obtain":[45],"respective":[47],"likelihood":[48],"scores":[49,54],"segment.":[52],"These":[53],"are":[55],"used":[56],"compute":[58],"dissimilarity":[60],"measure":[61],"between":[62],"pairs":[63],"carry":[68],"out":[69],"complete-linkage":[70],"clustering":[71],"the":[73,82,106,113,122,131],"into":[75],"non-speech":[78],"clusters.":[79],"compare":[81],"accuracy":[83],"our":[85,119,134],"method":[86],"state-of-the-art":[88],"standardised":[90],"VAD":[91],"techniques":[92],"demonstrate":[94,130],"an":[95],"absolute":[96],"improvement":[97],"15%":[99],"half-total":[101],"error":[102],"rate":[103],"(HTER)":[104],"over":[105],"best":[107],"performing":[108],"baseline":[109],"system":[110],"across":[112],"QUT-NOISE-TIMIT":[114],"database.":[115],"apply":[118],"approach":[120],"Audio-Visual":[123],"Database":[124],"American":[126],"English":[127],"(AVDBAE)":[128],"performance":[132],"algorithm":[135],"using":[137],"visual,":[138],"audio-visual":[139],"or":[140],"proposed":[142],"fusion":[143],"features.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}