{"id":"https://openalex.org/W2145939969","doi":"https://doi.org/10.1109/asru.2009.5373251","title":"Extended Minimum Classification Error Training in Voice Activity Detection","display_name":"Extended Minimum Classification Error Training in Voice Activity Detection","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2145939969","doi":"https://doi.org/10.1109/asru.2009.5373251","mag":"2145939969"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5088808388","display_name":"Takayuki Arakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takayuki Arakawa","raw_affiliation_strings":["Common Platform Software Research Laboratories, NEC Corporation Limited, Japan","Common Platform Software Res. Labs., NEC Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Common Platform Software Research Laboratories, NEC Corporation Limited, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Common Platform Software Res. Labs., NEC Corporation, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068150550","display_name":"Haitham Hassanieh","orcid":"https://orcid.org/0009-0004-9242-3269"},"institutions":[{"id":"https://openalex.org/I181401687","display_name":"American University","ror":"https://ror.org/052w4zt36","country_code":"US","type":"education","lineage":["https://openalex.org/I181401687"]},{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB","US"],"is_corresponding":false,"raw_author_name":"Haitham Al-Hassanieh","raw_affiliation_strings":["American University of Beirut, Lebanon","American University of Beiruit, Lebanon"],"affiliations":[{"raw_affiliation_string":"American University of Beirut, Lebanon","institution_ids":["https://openalex.org/I98635879"]},{"raw_affiliation_string":"American University of Beiruit, Lebanon","institution_ids":["https://openalex.org/I181401687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050358434","display_name":"Masanori Tsujikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanori Tsujikawa","raw_affiliation_strings":["Common Platform Software Research Laboratories, NEC Corporation Limited, Japan","Common Platform Software Res. Labs., NEC Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Common Platform Software Research Laboratories, NEC Corporation Limited, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Common Platform Software Res. Labs., NEC Corporation, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084065446","display_name":"Ryosuke Isotani","orcid":null},"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":"Ryosuke Isotani","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088808388"],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.18614058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"l","issue":null,"first_page":"232","last_page":"236"},"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":0.9994000196456909,"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":0.9991999864578247,"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/discriminative-model","display_name":"Discriminative model","score":0.8454456329345703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354109883308411},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6511672735214233},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6274352669715881},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6266133785247803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6228891015052795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5395050048828125},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4625481963157654},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43664079904556274},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4127885699272156},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3708408772945404}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8454456329345703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354109883308411},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6511672735214233},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6274352669715881},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6266133785247803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6228891015052795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5395050048828125},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4625481963157654},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43664079904556274},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4127885699272156},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3708408772945404},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W82354572","https://openalex.org/W86289693","https://openalex.org/W2129120544","https://openalex.org/W2153754015","https://openalex.org/W2165630397","https://openalex.org/W6682824448","https://openalex.org/W6683989643"],"related_works":["https://openalex.org/W2162582511","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"is":[4,16],"a":[5,59],"fundamental":[6],"part":[7],"of":[8,12,89,92],"speech":[9],"processing.":[10],"Combination":[11],"multiple":[13],"acoustic":[14],"features":[15],"an":[17],"effective":[18],"approach":[19],"to":[20],"make":[21],"VAD":[22],"more":[23],"robust":[24],"against":[25],"various":[26],"noise":[27],"conditions.":[28],"There":[29],"have":[30],"been":[31],"proposed":[32,67],"several":[33],"feature":[34,41],"combination":[35,70],"methods,":[36],"in":[37],"which":[38],"weights":[39,71],"for":[40,63],"values":[42],"are":[43],"optimized":[44],"based":[45],"on":[46],"minimum":[47],"classification":[48],"error":[49],"(MCE)":[50],"training.":[51],"We":[52],"improve":[53],"these":[54],"MCE-based":[55],"methods":[56],"by":[57],"introducing":[58],"novel":[60],"discriminative":[61],"function":[62],"whole":[64],"frames.":[65],"The":[66],"method":[68],"optimizes":[69],"taking":[72],"into":[73],"account":[74],"the":[75,87,90],"ratio":[76],"between":[77],"false":[78,81],"acceptance":[79],"and":[80],"rejection":[82],"rates":[83],"as":[84,86,96],"well":[85],"effect":[88],"use":[91],"shaping":[93],"procedures":[94],"such":[95],"hangover.":[97]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}