{"id":"https://openalex.org/W2144256180","doi":"https://doi.org/10.1109/slt.2010.5700838","title":"Analysis on speech characteristics for robust voice activity detection","display_name":"Analysis on speech characteristics for robust voice activity detection","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2144256180","doi":"https://doi.org/10.1109/slt.2010.5700838","mag":"2144256180"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2010.5700838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2010.5700838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Spoken Language Technology Workshop","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/A5039277089","display_name":"Miquel Espi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Miquel Espi","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Japan","The University of Tokyo, Graduate School of Information Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Graduate School of Information Science and Technology, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069120750","display_name":"Shigeki Miyabe","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Miyabe","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Japan","The University of Tokyo, Graduate School of Information Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Graduate School of Information Science and Technology, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100814456","display_name":"Takuya Nishimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Nishimoto","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Japan","The University of Tokyo, Graduate School of Information Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Graduate School of Information Science and Technology, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Japan","The University of Tokyo, Graduate School of Information Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Graduate School of Information Science and Technology, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003450550","display_name":"Shigeki Sagayama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Sagayama","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Japan","The University of Tokyo, Graduate School of Information Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Graduate School of Information Science and Technology, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039277089"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.3371,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6075736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"156"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7919290065765381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7539897561073303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7174654006958008},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6953608989715576},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5954374074935913},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4705864489078522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4600491523742676},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4523433744907379},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4163534939289093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38098204135894775},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24255326390266418}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7919290065765381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7539897561073303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174654006958008},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6953608989715576},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5954374074935913},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4705864489078522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4600491523742676},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4523433744907379},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4163534939289093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38098204135894775},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24255326390266418},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2010.5700838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2010.5700838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W36345725","https://openalex.org/W1563939609","https://openalex.org/W1970922112","https://openalex.org/W1994396704","https://openalex.org/W2098265087","https://openalex.org/W2100555417","https://openalex.org/W2100772705","https://openalex.org/W2103738385","https://openalex.org/W2129120544","https://openalex.org/W2153754015","https://openalex.org/W2167379017","https://openalex.org/W3142482781","https://openalex.org/W3147588286","https://openalex.org/W6674917984","https://openalex.org/W6676004468"],"related_works":["https://openalex.org/W1996690921","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W3160071434"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"about":[3],"effective":[4],"speech":[5,20,27,53],"characterization":[6],"for":[7],"off-line":[8],"voice":[9],"activity":[10],"detection":[11],"(VAD),":[12],"which":[13],"is":[14],"an":[15],"important":[16],"step":[17],"prior":[18],"to":[19,73],"data":[21],"mining.":[22],"Five":[23],"different":[24],"natures":[25],"of":[26,46,52,67,87,103],"are":[28],"examined;":[29],"energy,":[30],"spectral":[31,37,49],"shape,":[32],"periodicity,":[33],"phonetic":[34],"variation,":[35],"and":[36,70],"fluctuation,":[38],"the":[39,65,68,85,95,104],"latter":[40],"observed":[41],"from":[42],"a":[43],"new":[44],"point":[45],"view.":[47],"Specific":[48],"fluctuation":[50],"patterns":[51],"have":[54],"been":[55],"analyzed":[56],"using":[57],"multi-stage":[58],"Harmonic/Percussive":[59],"Sound":[60],"Separation":[61],"algorithm.":[62],"We":[63],"compared":[64],"performance":[66],"features,":[69],"various":[71],"combinations,":[72],"evaluate":[74],"their":[75],"robustness":[76],"in":[77],"multiple":[78],"noise":[79],"environments.":[80],"The":[81,91],"combined":[82],"approach":[83,99],"outperformed":[84],"baseline":[86],"CENSREC-1-C":[88],"evaluation":[89],"framework.":[90],"results":[92],"suggest":[93],"that":[94],"proposed":[96],"feature":[97],"extraction":[98],"can":[100],"improve":[101],"state":[102],"art":[105],"VAD":[106],"methods.":[107]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
