{"id":"https://openalex.org/W2509658457","doi":"https://doi.org/10.21437/interspeech.2016-642","title":"Non-Uniform Boosted MCE Training of Deep Neural Networks for Keyword Spotting","display_name":"Non-Uniform Boosted MCE Training of Deep Neural Networks for Keyword Spotting","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2509658457","doi":"https://doi.org/10.21437/interspeech.2016-642","mag":"2509658457"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-642","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biing-Hwang Juang","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":0.7765,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73792722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"770","last_page":"774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9976000189781189,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9588937759399414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421607971191406},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6944332122802734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6229726076126099},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5586430430412292},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5142009258270264},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4752088487148285},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4495583176612854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41708874702453613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37616872787475586},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.04421684145927429}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9588937759399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421607971191406},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6944332122802734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6229726076126099},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5586430430412292},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5142009258270264},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4752088487148285},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4495583176612854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41708874702453613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37616872787475586},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.04421684145927429},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-642","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W168261181","https://openalex.org/W1524333225","https://openalex.org/W1877570817","https://openalex.org/W1984806059","https://openalex.org/W1988745938","https://openalex.org/W2029733119","https://openalex.org/W2033565080","https://openalex.org/W2063689849","https://openalex.org/W2125234026","https://openalex.org/W2131342762","https://openalex.org/W2132991150","https://openalex.org/W2147768505","https://openalex.org/W2154887136","https://openalex.org/W2160815625"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W1989658893","https://openalex.org/W2545741539"],"abstract_inverted_index":{"Keyword":[0],"spotting":[1,37,119],"can":[2,29,49],"be":[3,50],"formulated":[4],"as":[5],"a":[6,81,124,152],"non-uniform":[7,55],"error":[8,58],"automatic":[9],"speech":[10,158],"recognition":[11],"(ASR)":[12],"problem.":[13],"It":[14],"has":[15],"been":[16],"demonstrated":[17],"[1]":[18],"that":[19,44,113],"this":[20,40],"new":[21],"formulation":[22],"with":[23,80],"the":[24,54,63,99,108,111,132,145,148,176],"nonuniform":[25],"MCE":[26],"training":[27],"technique":[28],"lead":[30],"to":[31,94],"improved":[32],"system":[33,83,120],"performance":[34,146],"in":[35,74],"keyword":[36,118],"applications.":[38],"In":[39],"paper,":[41],"we":[42],"demonstrate":[43],"deep":[45],"neural":[46],"networks":[47],"(DNNs)":[48],"successfully":[51],"trained":[52],"on":[53,65,72,151],"minimum":[56],"classification":[57],"(MCE)":[59],"criterion":[60],"which":[61,89],"weighs":[62],"errors":[64],"keywords":[66],"much":[67],"more":[68,101,115],"significantly":[69],"than":[70],"those":[71],"non-keywords":[73],"an":[75,167],"ASR":[76],"task.":[77],"The":[78,117,163],"integration":[79],"DNN-HMM":[82],"enables":[84],"modeling":[85],"of":[86,110,147,170,173],"multi-frame":[87],"distributions,":[88],"conventional":[90],"systems":[91],"find":[92],"difficult":[93],"accomplish.":[95],"To":[96],"further":[97],"improve":[98],"performance,":[100],"confusable":[102],"data":[103],"is":[104,121,134],"generated":[105],"by":[106],"boosting":[107],"likelihood":[109],"sentences":[112],"have":[114],"errors.":[116],"implemented":[122],"within":[123],"weighted":[125],"finite":[126],"state":[127],"transducer":[128],"(WFST)":[129],"framework":[130,150],"and":[131,139],"DNN":[133],"optimized":[135],"using":[136],"standard":[137],"backpropagation":[138],"stochastic":[140],"gradient":[141],"decent.":[142],"We":[143],"evaluate":[144],"proposed":[149,164],"large":[153],"vocabulary":[154],"spontaneous":[155],"conversational":[156],"telephone":[157],"dataset":[159],"(Switchboard-1":[160],"Release":[161],"2).":[162],"approach":[165],"achieves":[166],"absolute":[168],"figure":[169],"merit":[171],"improvement":[172],"3.65%":[174],"over":[175],"baseline":[177],"system.":[178]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}