{"id":"https://openalex.org/W1512475020","doi":"https://doi.org/10.21437/interspeech.2006-536","title":"Noise robust model-based voice activity detection","display_name":"Noise robust model-based voice activity detection","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W1512475020","doi":"https://doi.org/10.21437/interspeech.2006-536","mag":"1512475020"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-536","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5014325055","display_name":"\u00c1ngel de la Torre","orcid":"https://orcid.org/0000-0002-9736-5190"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"\u00c1ngel de la Torre","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067023995","display_name":"Javier Ram\u0131\u0301rez","orcid":"https://orcid.org/0000-0002-6229-2921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Ram\u00edrez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032065113","display_name":"Carmen Ben\u0131\u0301tez","orcid":"https://orcid.org/0000-0002-5407-8335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carmen Ben\u00edtez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000645757","display_name":"Jos\u00e9 C. Segura","orcid":"https://orcid.org/0000-0003-3746-0978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 C. Segura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013746163","display_name":"Luz Garc\u00eda","orcid":"https://orcid.org/0000-0001-5904-5412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L. Garc\u00eda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103257592","display_name":"Antonio J. Rubio","orcid":"https://orcid.org/0000-0003-3814-0335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio J. Rubio","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014325055"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6361,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.64343864,"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":"paper 1476","last_page":"Wed3A1O.1"},"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":0.9987999796867371,"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":0.9976000189781189,"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/speech-recognition","display_name":"Speech recognition","score":0.7728503942489624},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7565550804138184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6882264018058777},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5163701772689819},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.49826860427856445},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.47774285078048706},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4729043245315552},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.46697163581848145},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.46329817175865173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4425089955329895},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4368026852607727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3846486806869507},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36570972204208374},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20461991429328918},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06950649619102478}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7728503942489624},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7565550804138184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6882264018058777},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5163701772689819},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.49826860427856445},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.47774285078048706},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4729043245315552},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.46697163581848145},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.46329817175865173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4425089955329895},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4368026852607727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846486806869507},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36570972204208374},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20461991429328918},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06950649619102478},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-536","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W177521823","https://openalex.org/W1665196592","https://openalex.org/W1979012094","https://openalex.org/W2032362923","https://openalex.org/W2099145922","https://openalex.org/W2115717467","https://openalex.org/W2116520137","https://openalex.org/W2126597753","https://openalex.org/W2129120544","https://openalex.org/W2151484683","https://openalex.org/W2156038773","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W2028846388","https://openalex.org/W2072015625","https://openalex.org/W4295210860","https://openalex.org/W2438843077","https://openalex.org/W2117955483","https://openalex.org/W2161534637","https://openalex.org/W2010870899","https://openalex.org/W3168171120"],"abstract_inverted_index":{"We":[0,54],"propose":[1],"a":[2,44,49],"model-based":[3],"VAD":[4,74,78,99],"derived":[5],"from":[6],"the":[7,37,76,80,97,102],"Vector":[8],"Taylor":[9,113],"Series":[10],"(VTS)":[11],"approach.":[12],"A":[13],"Gaussian":[14,38,117],"mixture":[15,39],"(trained":[16],"with":[17],"clean":[18],"speech)":[19],"is":[20],"used":[21],"in":[22,83],"order":[23],"to":[24,40,72],"provide":[25],"an":[26],"appropriate":[27],"decision":[28],"rule":[29],"for":[30,48,59,66,89,93],"speech/non-speech":[31,60,84],"detection.":[32],"Additionally,":[33],"VTS":[34],"approach":[35,115],"adapts":[36],"noise":[41],"conditions,":[42],"yielding":[43],"stable":[45],"perfor-":[46],"mance":[47],"wide":[50],"range":[51],"of":[52],"SNRs.":[53],"have":[55],"evaluated":[56],"its":[57,64],"ability":[58],"detection":[61,110],"and":[62,92],"also":[63,100],"application":[65],"robust":[67],"speech":[68],"recognition.":[69],"When":[70,87],"compared":[71],"other":[73],"methods,":[75],"proposed":[77,98],"shows":[79],"best":[81,103],"trade-off":[82],"de-":[85],"tection.":[86],"applied":[88],"Wiener":[90,119],"Filtering":[91],"frame":[94],"drop-":[95],"ping,":[96],"provides":[101],"recognition":[104],"results.":[105],"Index":[106],"Terms:":[107],"voice":[108],"activity":[109],"(VAD),":[111],"vector":[112],"series":[114],"(VTS),":[116],"mixture,":[118],"filtering.":[120]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}