{"id":"https://openalex.org/W2097036989","doi":"https://doi.org/10.1186/1687-4722-2013-21","title":"Efficient voice activity detection algorithm using long-term spectral flatness measure","display_name":"Efficient voice activity detection algorithm using long-term spectral flatness measure","publication_year":2013,"publication_date":"2013-07-16","ids":{"openalex":"https://openalex.org/W2097036989","doi":"https://doi.org/10.1186/1687-4722-2013-21","mag":"2097036989"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2013-21","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2013-21","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-21","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-21","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018131622","display_name":"Yanna Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yanna Ma","raw_affiliation_strings":["Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, 152-8552, Japan","Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, Japan 152-8552#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, 152-8552, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, Japan 152-8552#TAB#","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026294946","display_name":"Akinori Nishihara","orcid":"https://orcid.org/0000-0002-0191-4328"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Nishihara","raw_affiliation_strings":["Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, 152-8552, Japan","Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, Japan 152-8552#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, 152-8552, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Communications and Integrated Systems, Tokyo Institute of Technology, Tokyo, Japan 152-8552#TAB#","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018131622"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":5.787,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.96603621,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2013","issue":"1","first_page":null,"last_page":null},"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":0.9994999766349792,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8373437523841858},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6963276863098145},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6521435976028442},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4781685471534729},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4519226551055908},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.43843764066696167},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4165266156196594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3846401274204254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28799208998680115},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.14889094233512878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373437523841858},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6963276863098145},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6521435976028442},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4781685471534729},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4519226551055908},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.43843764066696167},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4165266156196594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3846401274204254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28799208998680115},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.14889094233512878},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/1687-4722-2013-21","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2013-21","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-21","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004067564","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100659013","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2013-21","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2013-21","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-21","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2097036989.pdf","grobid_xml":"https://content.openalex.org/works/W2097036989.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W423095831","https://openalex.org/W1521990686","https://openalex.org/W1897045322","https://openalex.org/W1905983571","https://openalex.org/W1922223312","https://openalex.org/W1974387177","https://openalex.org/W2032474878","https://openalex.org/W2039851008","https://openalex.org/W2083569984","https://openalex.org/W2108367224","https://openalex.org/W2115717467","https://openalex.org/W2126693545","https://openalex.org/W2135445137","https://openalex.org/W2139415621","https://openalex.org/W2143448557","https://openalex.org/W2149675205","https://openalex.org/W2152395643","https://openalex.org/W2153644860","https://openalex.org/W2156038773","https://openalex.org/W2170116036","https://openalex.org/W2170644918","https://openalex.org/W2405388169","https://openalex.org/W2587899496","https://openalex.org/W3127686677","https://openalex.org/W3146874108","https://openalex.org/W3149794337","https://openalex.org/W4299415107"],"related_works":["https://openalex.org/W2071828724","https://openalex.org/W1994694193","https://openalex.org/W2098198482","https://openalex.org/W170831052","https://openalex.org/W4247725880","https://openalex.org/W1006721676","https://openalex.org/W2100854157","https://openalex.org/W1771058801","https://openalex.org/W2978471304","https://openalex.org/W4285346358"],"abstract_inverted_index":{"This":[0,30],"paper":[1],"proposes":[2],"a":[3,44],"novel":[4],"and":[5,26,48,84,87,109,111,166],"robust":[6],"voice":[7],"activity":[8],"detection":[9,36],"(VAD)":[10],"algorithm":[11,73,147],"utilizing":[12],"long-term":[13,128],"spectral":[14],"flatness":[15],"measure":[16],"(LSFM)":[17],"which":[18],"is":[19,60,134],"capable":[20],"of":[21,55,66,79,90,155],"working":[22],"at":[23],"10":[24],"dB":[25],"lower":[27],"signal-to-noise":[28],"ratios(SNRs).":[29],"new":[31,57],"LSFM-based":[32,118],"VAD":[33,119,132,151],"improves":[34],"speech":[35,167],"robustness":[37],"in":[38,92],"various":[39],"noisy":[40],"environments":[41],"by":[42,62],"employing":[43],"low-variance":[45],"spectrum":[46],"estimate":[47],"an":[49,64],"adaptive":[50,104],"threshold.":[51],"The":[52,71,141],"discriminative":[53],"power":[54],"the":[56,67,122,149,156],"LSFM":[58,69],"feature":[59],"shown":[61],"conducting":[63],"analysis":[65],"speech/non-speech":[68],"distributions.":[70],"proposed":[72,117,139,146],"was":[74],"evaluated":[75],"under":[76],"12":[77],"types":[78,89],"noises":[80,157,161],"(11":[81],"from":[82],"NOISEX-92":[83],"speech-shaped":[85],"noise)":[86],"five":[88],"SNR":[91],"core":[93],"TIMIT":[94],"test":[95],"corpus.":[96],"Comparisons":[97],"with":[98,137],"three":[99],"modern":[100],"standardized":[101],"algorithms":[102],"(ETSI":[103],"multi-rate":[105],"(AMR)":[106],"options":[107],"AMR1":[108],"AMR2":[110],"ITU-T":[112],"G.729)":[113],"demonstrate":[114],"that":[115,144],"our":[116,138,145],"scheme":[120,133,152],"achieved":[121],"best":[123],"average":[124],"accuracy":[125],"rate.":[126],"A":[127],"signal":[129],"variability":[130],"(LTSV)-based":[131],"also":[135],"compared":[136],"method.":[140],"results":[142],"show":[143],"outperforms":[148],"LTSV-based":[150],"for":[153],"most":[154],"considered":[158],"including":[159],"difficult":[160],"like":[162],"machine":[163],"gun":[164],"noise":[165],"babble":[168],"noise.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}