{"id":"https://openalex.org/W1558606374","doi":"https://doi.org/10.1109/icassp.2015.7178776","title":"A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture","display_name":"A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1558606374","doi":"https://doi.org/10.1109/icassp.2015.7178776","mag":"1558606374"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5040131037","display_name":"Ehsan Variani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ehsan Variani","raw_affiliation_strings":["Google, USA","Johns Hopkins Univ, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Johns Hopkins Univ, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik McDermott","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071956319","display_name":"Georg Heigold","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georg Heigold","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040131037"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":9.3503,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97778819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4270","last_page":"4274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9886000156402588,"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/discriminative-model","display_name":"Discriminative model","score":0.7887829542160034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7088032364845276},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6488659977912903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6412312984466553},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5689315795898438},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5686726570129395},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5458657145500183},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5381072759628296},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.529387891292572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.472713440656662},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4527358412742615},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.44721224904060364},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1441948413848877},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.053066372871398926},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05009418725967407}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7887829542160034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088032364845276},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6488659977912903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6412312984466553},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5689315795898438},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5686726570129395},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5458657145500183},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5381072759628296},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.529387891292572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.472713440656662},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4527358412742615},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.44721224904060364},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1441948413848877},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.053066372871398926},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05009418725967407},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1504820690","https://openalex.org/W1554663460","https://openalex.org/W1988095509","https://openalex.org/W2075925017","https://openalex.org/W2085684370","https://openalex.org/W2100966557","https://openalex.org/W2105099419","https://openalex.org/W2114016253","https://openalex.org/W2123237149","https://openalex.org/W2148464528","https://openalex.org/W2151402979","https://openalex.org/W2158808283","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2166661046","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2276256113","https://openalex.org/W2396630453","https://openalex.org/W2397682113","https://openalex.org/W2407712415","https://openalex.org/W2613634265","https://openalex.org/W4388297464","https://openalex.org/W6669906966","https://openalex.org/W6678292227","https://openalex.org/W6711808165","https://openalex.org/W6713968366","https://openalex.org/W6737658843"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W2146591867","https://openalex.org/W1578916557"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"and":[3,22,66,127],"evaluates":[4],"a":[5,16,82,89,100],"Gaussian":[6],"Mixture":[7],"Model":[8],"(GMM)":[9],"represented":[10],"as":[11],"the":[12,46,61,67,95,119,138,161,170],"last":[13],"layer":[14],"of":[15,60,79,86,107,115,163],"Deep":[17,108,139,145,171,179],"Neural":[18],"Network":[19],"(DNN)":[20],"architecture":[21,39],"jointly":[23],"optimized":[24],"with":[25,42,156],"all":[26],"previous":[27],"layers":[28,65],"using":[29,118,165],"Asynchronous":[30],"Stochastic":[31],"Gradient":[32],"Descent":[33],"(ASGD).":[34],"The":[35,50,71,143],"resulting":[36,184],"\u201cDeep":[37],"GMM\u201d":[38],"was":[40],"investigated":[41],"special":[43],"attention":[44],"to":[45,52,73,99,149,168,178],"following":[47],"issues:":[48],"(1)":[49],"extent":[51,72],"which":[53,74],"joint":[54],"optimization":[55,59,121,128],"improves":[56],"over":[57],"separate":[58],"DNN-based":[62],"feature":[63,173],"extraction":[64,174],"GMM":[68,96,109,140,172],"layer;":[69],"(2)":[70],"depth":[75],"(measured":[76],"in":[77,185],"number":[78,85],"layers,":[80],"for":[81,134],"matched":[83],"total":[84],"parameters)":[87],"helps":[88],"deep":[90],"generative":[91,141],"model":[92],"based":[93],"on":[94],"layer,":[97],"compared":[98],"vanilla":[101],"DNN":[102,113,158],"model;":[103],"(3)":[104],"Head-to-head":[105],"performance":[106],"architectures":[110,114],"vs.":[111],"equivalent":[112],"comparable":[116],"depth,":[117],"same":[120],"criterion":[122],"(frame-level":[123],"Cross":[124],"Entropy":[125],"(CE))":[126],"method":[129],"(ASGD);":[130],"(4)":[131],"Expanded":[132],"possibilities":[133],"modeling":[135],"offered":[136],"by":[137],"model.":[142],"proposed":[144],"GMMs":[146,181],"were":[147],"found":[148],"yield":[150],"Word":[151],"Error":[152],"Rates":[153],"(WERs)":[154],"competitive":[155],"state-of-the-art":[157],"systems,":[159],"at":[160],"cost":[162],"pre-training":[164],"standard":[166],"DNNs":[167],"initialize":[169],"layers.":[175],"An":[176],"extension":[177],"Subspace":[180],"is":[182],"described,":[183],"additional":[186],"gains.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-28T06:12:49.907903","created_date":"2025-10-10T00:00:00"}