{"id":"https://openalex.org/W80876278","doi":"https://doi.org/10.21437/interspeech.2006-539","title":"Evaluation of voice activity detection by combining multiple features with weight adaptation","display_name":"Evaluation of voice activity detection by combining multiple features with weight adaptation","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W80876278","doi":"https://doi.org/10.21437/interspeech.2006-539","mag":"80876278"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-539","doi":"https://doi.org/10.21437/interspeech.2006-539","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-539","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5109488356","display_name":"Yusuke Kida","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296","observed_orcids":["https://orcid.org/0000-0002-2686-2296"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4966,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.53529014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"paper 1152","last_page":"Wed3A1O.4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7064999938011169,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7064999938011169,"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/T10860","display_name":"Speech and Audio Processing","score":0.29249998927116394,"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":9.999999747378752e-05,"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/voice-activity-detection","display_name":"voice activity detection","score":0.9990000128746033},{"id":"https://openalex.org/keywords/feature-combination","display_name":"feature combination","score":0.5910000205039978},{"id":"https://openalex.org/keywords/weighted-combination","display_name":"weighted combination","score":0.5120000243186951},{"id":"https://openalex.org/keywords/minimum-classification-error-training","display_name":"minimum classification error training","score":0.9160000085830688},{"id":"https://openalex.org/keywords/noise-robust-speech-recognition","display_name":"noise-robust speech recognition","score":0.7770000100135803},{"id":"https://openalex.org/keywords/zero-crossing-rate","display_name":"zero-crossing rate","score":0.9700000286102295},{"id":"https://openalex.org/keywords/spectral-properties","display_name":"spectral properties","score":0.9039999842643738},{"id":"https://openalex.org/keywords/weight-adaptation","display_name":"weight adaptation","score":0.6200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7399202585220337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7352076172828674},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6257367134094238},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6099952459335327},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5878702998161316},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5656858682632446},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5362595319747925},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.497205525636673},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4606580436229706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4570193290710449},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4515988230705261},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3116565942764282},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-539","doi":"https://doi.org/10.21437/interspeech.2006-539","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-539","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W16670509","https://openalex.org/W86289693","https://openalex.org/W1536730100","https://openalex.org/W2129120544","https://openalex.org/W2162969672","https://openalex.org/W2166607750","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2145939969","https://openalex.org/W2103738385","https://openalex.org/W2008514512","https://openalex.org/W1634901816","https://openalex.org/W2106838754","https://openalex.org/W1976750768","https://openalex.org/W86289693","https://openalex.org/W2587899496","https://openalex.org/W1993449980","https://openalex.org/W2135056179"],"abstract_inverted_index":{"For":[0],"noise-robust":[1],"automatic":[2],"speech":[3,114],"recognition":[4],"(ASR),":[5],"we":[6,61,89],"propose":[7],"a":[8,17,25,85],"novel":[9],"voice":[10,116],"activity":[11,117],"detection":[12],"(VAD)":[13],"method":[14,94,103],"based":[15],"on":[16],"combination":[18,27,48,70],"of":[19,28,66,68,92],"multiple":[20],"features.":[21],"The":[22,45],"scheme":[23],"uses":[24],"weighted":[26],"four":[29],"conventionalVAD":[30],"features:":[31],"amplitude":[32],"level,":[33],"zero":[34],"crossing":[35],"rate,":[36],"spectral":[37],"information,":[38],"and":[39,72,75],"Gaussian":[40],"mixture":[41],"model":[42],"(GMM)":[43],"likelihood.":[44],"weights":[46,71,79],"for":[47],"are":[49],"adaptively":[50],"updated":[51],"using":[52],"minimum":[53],"classification":[54],"error":[55],"(MCE)":[56],"training.":[57],"In":[58],"this":[59],"paper,":[60],"first":[62],"investigate":[63],"the":[64,69,78,93,101],"effect":[65],"adaptation":[67,122],"GMM":[73],"parameters,":[74],"demonstrate":[76],"that":[77,100],"can":[80],"be":[81],"effectively":[82],"adapted":[83],"with":[84],"single":[86],"utterance.":[87],"Then,":[88],"present":[90],"application":[91],"to":[95],"ASR.":[96],"It":[97],"is":[98],"confirmed":[99],"proposed":[102],"significantly":[104],"outperforms":[105],"conventional":[106],"methods":[107],"in":[108],"various":[109],"noise":[110,121],"conditions.":[111],"Index":[112],"Terms:":[113],"recognition,":[115],"detection,":[118],"MCE":[119],"training,":[120]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}