{"id":"https://openalex.org/W2748717988","doi":"https://doi.org/10.21437/interspeech.2017-583","title":"Non-Uniform MCE Training of Deep Long Short-Term Memory Recurrent Neural Networks for Keyword Spotting","display_name":"Non-Uniform MCE Training of Deep Long Short-Term Memory Recurrent Neural Networks for Keyword Spotting","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2748717988","doi":"https://doi.org/10.21437/interspeech.2017-583","mag":"2748717988"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-583","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhong Meng","raw_affiliation_strings":[],"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":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.39,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7040577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3547","last_page":"3551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9969000220298767,"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":0.9211524724960327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7620542049407959},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7138077616691589},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6788970232009888},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.6416078805923462},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6363323926925659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5540845394134521},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5058755278587341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4814009666442871},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4773271679878235}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9211524724960327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620542049407959},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7138077616691589},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6788970232009888},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.6416078805923462},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6363323926925659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5540845394134521},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5058755278587341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814009666442871},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4773271679878235},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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.2017-583","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W114193738","https://openalex.org/W854541894","https://openalex.org/W1485222997","https://openalex.org/W1496120315","https://openalex.org/W1524333225","https://openalex.org/W1877570817","https://openalex.org/W1988745938","https://openalex.org/W2005708641","https://openalex.org/W2015688877","https://openalex.org/W2029733119","https://openalex.org/W2033565080","https://openalex.org/W2056986588","https://openalex.org/W2064675550","https://openalex.org/W2085628288","https://openalex.org/W2122797512","https://openalex.org/W2125234026","https://openalex.org/W2131342762","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2291513470","https://openalex.org/W2293634267","https://openalex.org/W2509658457","https://openalex.org/W2636483419"],"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/W2117995638","https://openalex.org/W1989658893"],"abstract_inverted_index":{"It":[0],"has":[1],"been":[2],"shown":[3],"in":[4,76],"[1,":[5],"2]":[6],"that":[7,112],"improved":[8],"performance":[9],"can":[10],"be":[11],"achieved":[12],"by":[13],"formulating":[14],"the":[15,62,67,71,73,78,81,89,93,97,107,113,118,159,162,174],"keyword":[16,136,175],"spotting":[17,137,176],"as":[18],"a":[19,32],"non-uniform":[20,48,104],"error":[21,52,59],"automatic":[22],"speech":[23,98],"recognition":[24,114],"problem.":[25],"In":[26],"this":[27],"work,":[28],"we":[29],"discriminatively":[30],"train":[31],"deep":[33,164],"bidirectional":[34],"long":[35],"short-term":[36],"memory":[37],"(BLSTM)":[38],"\u2013":[39],"hidden":[40],"Markov":[41],"model":[42,46],"(HMM)":[43],"based":[44],"acoustic":[45],"with":[47,170],"boosted":[49],"minimum":[50],"classification":[51],"(BMCE)":[53],"criterion":[54,172],"which":[55],"imposes":[56],"more":[57],"significant":[58],"cost":[60],"on":[61,66,178],"keywords":[63,119],"than":[64],"those":[65],"non-keywords.":[68],"By":[69],"introducing":[70],"BLSTM,":[72],"context":[74],"information":[75],"both":[77],"past":[79],"and":[80,85,92,131,152,161],"future":[82],"are":[83,100,120],"stored":[84],"updated":[86],"to":[87,117],"predict":[88],"desired":[90],"output":[91],"long-term":[94],"dependencies":[95],"within":[96,141],"signal":[99],"well":[101],"captured.":[102],"With":[103],"BMCE":[105],"objective,":[106],"BLSTM":[108,124,160],"is":[109,125,139],"trained":[110,169],"so":[111],"errors":[115],"related":[116],"remarkably":[121],"reduced.":[122],"The":[123,135,147],"optimized":[126],"using":[127],"backpropagation":[128],"through":[129],"time":[130],"stochastic":[132],"gradient":[133],"descent.":[134],"system":[138],"implemented":[140],"weighted":[142],"finite":[143],"state":[144],"transducer":[145],"framework.":[146],"proposed":[148],"method":[149],"achieves":[150],"5.49%":[151],"7.37%":[153],"absolute":[154],"figure-of-merit":[155],"improvements":[156],"respectively":[157],"over":[158],"feedforward":[163],"neural":[165],"network":[166],"baseline":[167],"systems":[168],"cross-entropy":[171],"for":[173],"task":[177],"Switchboard-1":[179],"Release":[180],"2":[181],"dataset.":[182]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}