{"id":"https://openalex.org/W2801018181","doi":"https://doi.org/10.1109/icassp.2018.8461652","title":"Robust Feature Clustering for Unsupervised Speech Activity Detection","display_name":"Robust Feature Clustering for Unsupervised Speech Activity Detection","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2801018181","doi":"https://doi.org/10.1109/icassp.2018.8461652","mag":"2801018181"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5033701513","display_name":"Harishchandra Dubey","orcid":"https://orcid.org/0000-0003-0476-3884"},"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":"Harishchandra Dubey","raw_affiliation_strings":["Robust Speech Technologies Lab, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robust Speech Technologies Lab, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469714","display_name":"Abhijeet Sangwan","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":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":["Robust Speech Technologies Lab, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robust Speech Technologies Lab, 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"},"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":["Robust Speech Technologies Lab, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robust Speech Technologies Lab, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6627,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8487258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2726","last_page":"2730"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9997000098228455,"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/nist","display_name":"NIST","score":0.8383873701095581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7932332754135132},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7578822374343872},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7456672191619873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6253073811531067},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5506526827812195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48516708612442017},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.46120184659957886},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4456789195537567},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.416671484708786},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4166325330734253},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3903582692146301}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8383873701095581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932332754135132},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7578822374343872},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7456672191619873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6253073811531067},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5506526827812195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48516708612442017},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.46120184659957886},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4456789195537567},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.416671484708786},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4166325330734253},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3903582692146301},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1536583098","https://openalex.org/W1985242443","https://openalex.org/W1994387177","https://openalex.org/W1997817740","https://openalex.org/W2023582935","https://openalex.org/W2098265087","https://openalex.org/W2115717467","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2158146178","https://openalex.org/W2295098554","https://openalex.org/W2353261545","https://openalex.org/W2401364490","https://openalex.org/W2403186097","https://openalex.org/W2514407679","https://openalex.org/W2525821395","https://openalex.org/W2586681212","https://openalex.org/W2606468144","https://openalex.org/W2738707637","https://openalex.org/W2976826970","https://openalex.org/W6632152668","https://openalex.org/W6697089127","https://openalex.org/W6712995851","https://openalex.org/W6713037448"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"In":[0],"certain":[1],"applications":[2],"such":[3],"as":[4],"zero-resource":[5],"speech":[6,20],"processing":[7],"or":[8,35],"very-low":[9],"resource":[10],"speech-language":[11],"systems,":[12],"it":[13],"might":[14],"not":[15,66],"be":[16],"feasible":[17],"to":[18,45,91,96],"collect":[19],"activity":[21],"detection":[22],"(SAD)":[23],"annotations.":[24],"However,":[25],"the":[26,46,81,97,102,119,125],"state-of-the-art":[27],"supervised":[28],"SAD":[29,58,63],"techniques":[30],"based":[31],"on":[32,104],"neural":[33],"networks":[34],"other":[36],"machine":[37],"learning":[38],"methods":[39],"require":[40],"annotated":[41],"training":[42],"data":[43],"matched":[44],"target":[47],"domain.":[48],"This":[49],"paper":[50],"establish":[51],"a":[52,76],"clustering":[53],"approach":[54,70,123],"for":[55,60,79],"fully":[56],"unsupervised":[57],"useful":[59],"cases":[61],"where":[62],"annotations":[64],"are":[65],"available.":[67],"The":[68,116],"proposed":[69,98,122],"leverages":[71],"Harti-gan":[72],"dip":[73,88],"test":[74],"in":[75],"recursive":[77],"strategy":[78],"segmenting":[80],"feature":[82],"space":[83],"into":[84],"prominent":[85],"modes.":[86],"Statistical":[87],"is":[89],"invariant":[90],"distortions":[92],"that":[93],"lends":[94],"robustness":[95],"method.":[99],"We":[100],"evaluate":[101],"method":[103],"NIST":[105,109],"OpenSAD":[106],"2015":[107],"and":[108],"OpenSAT":[110],"2017":[111],"public":[112],"safety":[113],"communications":[114],"data.":[115],"results":[117],"showed":[118],"superiority":[120],"of":[121],"over":[124],"two-component":[126],"GMM":[127],"baseline.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}