{"id":"https://openalex.org/W2406310406","doi":"https://doi.org/10.21437/interspeech.2012-531","title":"Acoustic and data-driven features for robust speech activity detection","display_name":"Acoustic and data-driven features for robust speech activity detection","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2406310406","doi":"https://doi.org/10.21437/interspeech.2012-531","mag":"2406310406"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-531","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047596805","display_name":"Sri Harish Mallidi","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sri Harish Mallidi","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077438382","display_name":"Thomas Janu","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Janu","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["University of Maryland - College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063689450","display_name":"Xin\u2010Hui Zhou","orcid":"https://orcid.org/0000-0001-6849-6979"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinhui Zhou","raw_affiliation_strings":["University of Maryland - College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057113698","display_name":"Shihab Shamma","orcid":"https://orcid.org/0000-0002-1283-6804"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shihab Shamma","raw_affiliation_strings":["University of Maryland - College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110640042","display_name":"Tim Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Ng","raw_affiliation_strings":["BBN Technologies"],"affiliations":[{"raw_affiliation_string":"BBN Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389658","display_name":"Bing Zhang","orcid":"https://orcid.org/0000-0001-7311-9844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Zhang","raw_affiliation_strings":["BBN Technologies"],"affiliations":[{"raw_affiliation_string":"BBN Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Nguyen","raw_affiliation_strings":["BBN Technologies"],"affiliations":[{"raw_affiliation_string":"BBN Technologies","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034173999","display_name":"Spyros Matsoukas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spyros Matsoukas","raw_affiliation_strings":["BBN Technologies"],"affiliations":[{"raw_affiliation_string":"BBN Technologies","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.4773,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92242087,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1985","last_page":"1988"},"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7602230906486511},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6950421333312988},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6754149198532104},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5362085700035095},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5247036218643188},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5159916877746582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511083722114563},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5049436688423157},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.469200074672699},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4652595818042755},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45856085419654846},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.413798451423645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24291807413101196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602230906486511},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6950421333312988},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6754149198532104},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5362085700035095},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5247036218643188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5159916877746582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511083722114563},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5049436688423157},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.469200074672699},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4652595818042755},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45856085419654846},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.413798451423645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24291807413101196}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-531","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.261.587","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.261.587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Esamuel/pdfs/sad.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W15516501","https://openalex.org/W2032362923","https://openalex.org/W2054139811","https://openalex.org/W2085085647","https://openalex.org/W2130426352","https://openalex.org/W2132214951","https://openalex.org/W2170580867","https://openalex.org/W2170644918","https://openalex.org/W2272205801","https://openalex.org/W2403186097","https://openalex.org/W2887979278","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2598586350","https://openalex.org/W1979693044","https://openalex.org/W1523214805","https://openalex.org/W4294771049","https://openalex.org/W2559040841","https://openalex.org/W2341426843","https://openalex.org/W1999835922","https://openalex.org/W2131711534","https://openalex.org/W2145696007","https://openalex.org/W2186020725"],"abstract_inverted_index":{"In":[0],"this":[1,83],"paper":[2],"we":[3],"evaluate":[4],"different":[5],"features":[6,21,36,43,55,81],"for":[7,82,115,136],"speech":[8,26,30,68,139],"activity":[9],"detection":[10],"(SAD).":[11],"Several":[12],"signal":[13,106],"processing":[14,137],"techniques":[15,88,171],"are":[16,76,107,125],"used":[17,78,108,126],"to":[18,127],"derive":[19],"acoustic":[20,35,168],"that":[22],"capture":[23],"attributes":[24],"of":[25,64,67,91,102,104,138,156],"useful":[27],"in":[28,32,172],"differentiating":[29],"segments":[31],"noise.":[33],"The":[34,160],"include":[37],"short-term":[38],"spectral":[39],"features,":[40],"long-term":[41],"modulation":[42],"both":[44],"derived":[45],"using":[46,57],"Frequency":[47],"Domain":[48],"Linear":[49],"Prediction":[50],"(FDLP),":[51],"and":[52,69],"joint":[53],"spectro-temporal":[54],"extracted":[56],"2D":[58],"filters":[59],"on":[60,132],"a":[61,72],"cortical":[62],"representation":[63],"speech.":[65],"Posteriors":[66],"non-speech":[70],"from":[71,121,140],"trained":[73],"multi-layer":[74],"perceptron":[75],"also":[77],"as":[79],"data-driven":[80],"task.":[84],"These":[85],"feature":[86,94,119,169],"extraction":[87,95,170],"form":[89],"part":[90],"an":[92],"elaborate":[93],"front-end":[96,124,162],"where":[97],"information":[98],"spanning":[99],"several":[100],"hundreds":[101],"milliseconds":[103],"the":[105,122,150],"along":[109],"with":[110],"heteroscedastic":[111],"linear":[112],"discriminant":[113],"analysis":[114],"dimensionality":[116],"reduction.":[117],"Processed":[118],"outputs":[120],"proposed":[123,161],"train":[128],"SAD":[129],"systems":[130],"based":[131],"Gaussian":[133],"mixture":[134],"models":[135],"multiple":[141],"languages":[142],"transmitted":[143],"over":[144],"noisy":[145,174],"radio":[146],"communication":[147],"channels":[148],"under":[149],"ongoing":[151],"DARPA":[152],"Robust":[153],"Automatic":[154],"Transcription":[155],"Speech":[157],"(RATS)":[158],"program.":[159],"performs":[163],"significantly":[164],"better":[165],"than":[166],"standard":[167],"these":[173],"conditions.":[175]},"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":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}