{"id":"https://openalex.org/W2765399676","doi":"https://doi.org/10.1109/ncc.2017.8077146","title":"Role of voice activity detection methods for the speakers in the wild challenge","display_name":"Role of voice activity detection methods for the speakers in the wild challenge","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2765399676","doi":"https://doi.org/10.1109/ncc.2017.8077146","mag":"2765399676"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2017.8077146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5006575035","display_name":"Sarfaraz Jelil","orcid":"https://orcid.org/0009-0001-4690-529X"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarfaraz Jelil","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S.R. Mahadeva Prasanna","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036693781","display_name":"Rohit Sinha","orcid":"https://orcid.org/0000-0002-0419-6501"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohit Sinha","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9998999834060669,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767823338508606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6590758562088013},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5644605159759521},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.516428530216217},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5083062052726746},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4565197825431824},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4243677258491516},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39372849464416504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3511285185813904},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0929710865020752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767823338508606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6590758562088013},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5644605159759521},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.516428530216217},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5083062052726746},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4565197825431824},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4243677258491516},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39372849464416504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3511285185813904},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0929710865020752},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc.2017.8077146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1980931161","https://openalex.org/W1994244061","https://openalex.org/W2007119422","https://openalex.org/W2034766634","https://openalex.org/W2069976350","https://openalex.org/W2090716422","https://openalex.org/W2096594917","https://openalex.org/W2121061347","https://openalex.org/W2129120544","https://openalex.org/W2150769028","https://openalex.org/W2395750323","https://openalex.org/W2516764878","https://openalex.org/W6674438166"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"One":[0,71],"of":[1,9,29,37,55,72,94,166,168],"the":[2,6,27,35,52,56,59,75,81,92,97,103,107,116,128,139,158,164,169],"major":[3],"reasons":[4],"for":[5],"performance":[7,125],"degradation":[8],"a":[10],"speaker":[11],"verification":[12],"(SV)":[13],"system":[14,122,131],"in":[15,43,58,68,106,115,132,157],"real-world":[16],"conditions":[17],"is":[18,74,83,143],"its":[19],"inability":[20],"to":[21,26,127,148],"spot":[22],"speech":[23],"regions":[24],"due":[25],"presence":[28],"noise.":[30],"This":[31],"work":[32],"focuses":[33],"on":[34,51,85],"role":[36],"voice":[38],"activity":[39],"detection":[40],"(VAD)":[41],"methods":[42],"alleviating":[44],"such":[45],"shortcomings.":[46],"The":[47,118],"experiments":[48],"are":[49,66,100,161],"conducted":[50],"core-core":[53],"task":[54],"speakers":[57],"wild":[60],"(SITW)":[61],"challenge.":[62],"Two":[63],"VAD":[64,79,120],"approaches":[65],"explored":[67],"this":[69],"work.":[70],"them":[73],"recently":[76],"proposed":[77],"self-adaptive":[78,119,149],"and":[80,109],"other":[82],"based":[84,121,130,141],"vowel-like":[86],"region":[87],"(VLR)":[88],"detection.":[89],"For":[90],"evaluating":[91],"effectiveness":[93],"these":[95,152],"approaches,":[96],"SV":[98,159],"systems":[99],"developed":[101],"using":[102],"i-vector":[104],"framework":[105],"front-end":[108],"probabilistic":[110],"linear":[111],"discriminant":[112],"analysis":[113],"(PLDA)":[114],"back-end.":[117],"shows":[123],"better":[124],"compared":[126,147],"VLR":[129,140],"high":[133],"SNR":[134],"condition.":[135],"Under":[136],"degraded":[137],"conditions,":[138],"method":[142],"relatively":[144],"more":[145],"robust":[146],"VAD.":[150],"Exploiting":[151],"complementary":[153],"features,":[154],"significant":[155],"improvements":[156],"performances":[160],"noted":[162],"with":[163],"fusion":[165],"scores":[167],"two":[170],"systems.":[171]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}