{"id":"https://openalex.org/W2181395726","doi":"https://doi.org/10.21437/interspeech.2013-201","title":"Multi-band long-term signal variability features for robust voice activity detection","display_name":"Multi-band long-term signal variability features for robust voice activity detection","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2181395726","doi":"https://doi.org/10.21437/interspeech.2013-201","mag":"2181395726"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-201","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5072740718","display_name":"Andreas Tsiartas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andreas Tsiartas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029799530","display_name":"Theodora Chaspari","orcid":"https://orcid.org/0000-0002-7603-8633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Theodora Chaspari","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010475442","display_name":"Nassos Katsamanis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nassos Katsamanis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046000500","display_name":"Prasanta Ghosh","orcid":"https://orcid.org/0000-0002-2925-1802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351429","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-4303-2438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113701682","display_name":"Maarten Van Segbroeck","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maarten Van Segbroeck","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084949286","display_name":"Alexandros Potamianos","orcid":"https://orcid.org/0009-0007-1532-5288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandros Potamianos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5072740718"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.469,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95144664,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"718","last_page":"722"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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":0.7589781284332275},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7583699226379395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6992822885513306},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6165194511413574},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5895317792892456},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5774174332618713},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5649387240409851},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5099695920944214},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4791364371776581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4515697658061981},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44896769523620605},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34488222002983093},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23194316029548645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589781284332275},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7583699226379395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6992822885513306},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6165194511413574},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5895317792892456},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5774174332618713},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5649387240409851},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5099695920944214},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4791364371776581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4515697658061981},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44896769523620605},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34488222002983093},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23194316029548645},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-201","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1501620","https://openalex.org/W304112886","https://openalex.org/W1490760466","https://openalex.org/W1540596182","https://openalex.org/W1673191017","https://openalex.org/W1905983571","https://openalex.org/W2003662252","https://openalex.org/W2023684629","https://openalex.org/W2103869314","https://openalex.org/W2107926288","https://openalex.org/W2115717467","https://openalex.org/W2119393553","https://openalex.org/W2126693545","https://openalex.org/W2148154194","https://openalex.org/W2403186097","https://openalex.org/W2887979278"],"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":[0,15,67],"this":[1],"paper,":[2],"we":[3,17,72],"propose":[4],"robust":[5,115],"features":[6],"for":[7,63,85],"the":[8,19,34,39,53,59,78,82,100],"problem":[9],"of":[10,33,43,69,81,104],"voice":[11,64,112],"activity":[12,65,113],"detection":[13],"(VAD).":[14],"particular,":[16],"extend":[18],"long":[20],"term":[21],"signal":[22],"variability":[23],"(LTSV)":[24],"feature":[25,116],"to":[26],"accommodate":[27],"multiple":[28],"spectral":[29],"bands.":[30],"The":[31],"motivation":[32],"multi-band":[35,54],"approach":[36,55],"stems":[37],"from":[38],"non-uniform":[40],"frequency":[41],"scale":[42],"speech":[44,110],"phonemes":[45],"and":[46,94],"noise":[47],"characteristics.":[48],"Our":[49],"analysis":[50],"shows":[51],"that":[52],"offers":[56],"advantages":[57],"over":[58,77],"single":[60],"band":[61],"LTSV":[62],"detection.":[66],"terms":[68],"classification":[70],"accuracy,":[71],"show":[73],"0.3%-61.2%":[74],"relative":[75],"improvement":[76],"best":[79],"accuracy":[80],"baselines":[83],"considered":[84],"7":[86],"out":[87],"8":[88],"different":[89],"noisy":[90,105,109],"channels.":[91],"Experimental":[92],"results,":[93],"error":[95],"analysis,":[96],"are":[97],"reported":[98],"on":[99],"DARPA":[101],"RATS":[102],"corpora":[103],"speech.":[106],"Index":[107],"Terms:":[108],"data,":[111],"detection,":[114],"extraction":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}