{"id":"https://openalex.org/W2765885341","doi":"https://doi.org/10.1109/ncc.2017.8077072","title":"Voice activity detection for children's read speech recognition in noisy conditions","display_name":"Voice activity detection for children's read speech recognition in noisy conditions","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2765885341","doi":"https://doi.org/10.1109/ncc.2017.8077072","mag":"2765885341"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2017.8077072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077072","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":"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/A5059672669","display_name":"Ankita Pasad","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ankita Pasad","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029001285","display_name":"Kamini Sabu","orcid":"https://orcid.org/0000-0002-1866-6260"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kamini Sabu","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084496610","display_name":"Preeti Rao","orcid":"https://orcid.org/0000-0002-2842-8450"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preeti Rao","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Bombay, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059672669"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58697302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9998000264167786,"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":0.9998000264167786,"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/speech-recognition","display_name":"Speech recognition","score":0.7893004417419434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392428517341614},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7234188318252563},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6715010404586792},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6605396270751953},{"id":"https://openalex.org/keywords/reading-aloud","display_name":"Reading aloud","score":0.6031915545463562},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5781023502349854},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.47767409682273865},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.45420050621032715},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4183606207370758},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4110196828842163},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.39397919178009033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3351026177406311},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17971748113632202},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10769757628440857}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7893004417419434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392428517341614},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7234188318252563},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6715010404586792},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6605396270751953},{"id":"https://openalex.org/C2993756790","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading aloud","level":3,"score":0.6031915545463562},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5781023502349854},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.47767409682273865},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45420050621032715},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4183606207370758},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4110196828842163},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.39397919178009033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3351026177406311},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17971748113632202},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10769757628440857},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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:10.1109/ncc.2017.8077072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077072","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":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W55930003","https://openalex.org/W1992475611","https://openalex.org/W2077768438","https://openalex.org/W2089240210","https://openalex.org/W2112844139","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2181395726","https://openalex.org/W2394998899","https://openalex.org/W2535438430","https://openalex.org/W3015006758","https://openalex.org/W3142482781","https://openalex.org/W3145319331","https://openalex.org/W6602294394","https://openalex.org/W6685770725","https://openalex.org/W6775821556"],"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/W2248536413","https://openalex.org/W2383417046","https://openalex.org/W4386336391","https://openalex.org/W3217417050","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Recordings":[0],"of":[1,17,39,73,121,127,137],"read-aloud":[2],"stories":[3],"by":[4,63],"children":[5],"in":[6,113],"a":[7,114],"school":[8],"setting":[9],"can":[10],"be":[11,30],"used":[12],"to":[13,29,33,71,85,89,93,98,134],"provide":[14],"an":[15],"assessment":[16],"reading":[18],"skills":[19],"via":[20],"automatic":[21],"speech":[22],"recognition":[23],"(ASR).":[24],"ASR,":[25],"however,":[26],"is":[27,130],"known":[28],"highly":[31],"susceptible":[32],"background":[34,47,51],"noise.":[35],"The":[36],"unusual":[37],"variety":[38],"foreground":[40],"(breath":[41],"release,":[42],"mic":[43],"pops,":[44],"etc.)":[45,54],"and":[46,104],"(children":[48],"playing,":[49],"distinct":[50],"talker,":[52],"wind,":[53],"non-speech":[55,79,91],"sounds":[56],"makes":[57],"this":[58],"application":[59],"particularly":[60],"challenging.":[61],"Motivated":[62],"the":[64,74,94,122,128,135,138],"observation":[65],"on":[66],"real-world":[67],"data":[68],"that":[69],"close":[70],"50%":[72],"recorded":[75],"audio":[76],"comprises":[77],"purely":[78],"activity,":[80],"we":[81],"investigate":[82],"robust":[83],"approaches":[84],"voice":[86,123],"activity":[87,124],"detection":[88,125],"eliminate":[90],"segments":[92],"extent":[95],"possible":[96],"prior":[97],"ASR.":[99],"We":[100],"have":[101],"exploited":[102],"energy-based":[103],"harmonicity-based":[105],"features":[106],"coupled":[107],"with":[108,132],"suitable":[109],"temporal":[110],"smoothing":[111],"constraints":[112],"two-pass":[115],"noise":[116,139],"preprocessing":[117],"system.":[118],"A":[119],"discussion":[120],"performance":[126],"system":[129],"presented":[131],"reference":[133],"characteristics":[136],"types.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}