{"id":"https://openalex.org/W4240438151","doi":"https://doi.org/10.1109/iscslp.2014.6936716","title":"Robust voice activity detection based on concept of modulation transfer function in noisy reverberant environments","display_name":"Robust voice activity detection based on concept of modulation transfer function in noisy reverberant environments","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W4240438151","doi":"https://doi.org/10.1109/iscslp.2014.6936716"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","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/A5005931734","display_name":"Shota Morita","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shota Morita","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, JAPAN"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, JAPAN","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, JAPAN"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, JAPAN","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["Universal Communication Research Institute, National Institute of Information and Communications Technology, JAPAN"],"affiliations":[{"raw_affiliation_string":"Universal Communication Research Institute, National Institute of Information and Communications Technology, JAPAN","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Hokuriku Sentan Kagaku Gijutsu Daigakuin Daigaku, Nomi, Ishikawa, JP"],"affiliations":[{"raw_affiliation_string":"Hokuriku Sentan Kagaku Gijutsu Daigakuin Daigaku, Nomi, Ishikawa, JP","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005931734"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.8734,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77269834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"658 661","issue":null,"first_page":"108","last_page":"112"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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/reverberation","display_name":"Reverberation","score":0.7670449614524841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479666471481323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7326034307479858},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6770282983779907},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6187363266944885},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6034948825836182},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.5628969669342041},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5134721398353577},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47691914439201355},{"id":"https://openalex.org/keywords/noise-power","display_name":"Noise power","score":0.4663502275943756},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4562751352787018},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4254443645477295},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.36224251985549927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24958637356758118},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23151174187660217},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13920873403549194},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11455479264259338},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.052242785692214966}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7670449614524841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479666471481323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7326034307479858},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6770282983779907},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6187363266944885},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6034948825836182},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.5628969669342041},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5134721398353577},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47691914439201355},{"id":"https://openalex.org/C203234222","wikidata":"https://www.wikidata.org/wiki/Q2133519","display_name":"Noise power","level":3,"score":0.4663502275943756},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4562751352787018},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4254443645477295},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.36224251985549927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24958637356758118},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23151174187660217},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13920873403549194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11455479264259338},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.052242785692214966},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W246278971","https://openalex.org/W1563939609","https://openalex.org/W1967751524","https://openalex.org/W1974387177","https://openalex.org/W2038728370","https://openalex.org/W2056608640","https://openalex.org/W2059520982","https://openalex.org/W2086286498","https://openalex.org/W2092585129","https://openalex.org/W2121132080","https://openalex.org/W2133059825","https://openalex.org/W2141102245","https://openalex.org/W2149053750","https://openalex.org/W2163861656","https://openalex.org/W2395598773","https://openalex.org/W2400766871","https://openalex.org/W2404762821","https://openalex.org/W6677751794","https://openalex.org/W6680096826","https://openalex.org/W6713558335"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2135485548","https://openalex.org/W2770624987","https://openalex.org/W2072884270","https://openalex.org/W4256175191","https://openalex.org/W2890075319","https://openalex.org/W2356426224","https://openalex.org/W2734909224","https://openalex.org/W2373767407"],"abstract_inverted_index":{"Most":[0],"of":[1,41,68,77],"the":[2,39,78,89,94,109,122,143,149],"current":[3],"voice":[4],"activity":[5],"detection":[6],"(VAD)":[7],"algorithms":[8],"deal":[9],"with":[10,16],"clean":[11],"(noiseless)":[12],"speech":[13,15,34,55,95,103,124],"or":[14,27],"additive":[17,90],"noise":[18,42,81,91],"conditions.":[19],"They":[20],"cannot":[21],"work":[22,28],"in":[23,59,133],"noisy":[24,60,138],"reverberant":[25,61,139],"environments":[26,140],"poorly":[29],"if":[30],"they":[31],"do,":[32],"because":[33],"is":[35,74,85,101,117],"smeared":[36],"due":[37],"to":[38,80,87],"effects":[40],"and":[43,56,136],"reverberation.":[44],"This":[45],"paper":[46],"proposes":[47],"a":[48,102,118],"robust":[49],"VAD":[50,65,132,145,151],"algorithm":[51,66,146],"for":[52,127],"precisely":[53],"detecting":[54],"non-speech":[57],"periods":[58],"environments.":[62],"The":[63,71,98,114],"proposed":[64,144],"consists":[67],"three":[69],"blocks.":[70],"first":[72],"block":[73,100,116],"an":[75],"estimation":[76],"signal":[79],"ratio":[82],"(SNR)":[83],"which":[84],"used":[86],"mitigate":[88],"effect":[92],"on":[93,108,121,131],"power":[96,104,125],"envelope.":[97],"second":[99],"envelope":[105,126],"dereverberation":[106],"based":[107],"modulation":[110],"transfer":[111],"function":[112],"concept.":[113],"last":[115],"threshold":[119],"processing":[120],"dereverberated":[123],"speech/non-speech":[128],"decision.":[129],"Experiments":[130],"both":[134],"artificial":[135],"realistic":[137],"revealed":[141],"that":[142],"significantly":[147],"outperforms":[148],"conventional":[150],"algorithms.":[152]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
