{"id":"https://openalex.org/W2026369565","doi":"https://doi.org/10.1109/icassp.2014.6853589","title":"Improving deep neural network acoustic models using generalized maxout networks","display_name":"Improving deep neural network acoustic models using generalized maxout networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2026369565","doi":"https://doi.org/10.1109/icassp.2014.6853589","mag":"2026369565"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5074213973","display_name":"Xiaohui Zhang","orcid":null},"institutions":[{"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":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017882589","display_name":"Jan Trmal","orcid":null},"institutions":[{"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":false,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"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":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"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":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language & Speech Process. & Human Language Technol., Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":275,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"215","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733797550201416},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6349680423736572},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5677680969238281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4728562831878662},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4409600794315338},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4383646249771118},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3289932906627655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733797550201416},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6349680423736572},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5677680969238281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4728562831878662},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4409600794315338},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4383646249771118},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3289932906627655}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W1524333225","https://openalex.org/W1864026867","https://openalex.org/W1904365287","https://openalex.org/W1968419113","https://openalex.org/W1981706894","https://openalex.org/W2000200144","https://openalex.org/W2035424729","https://openalex.org/W2037740282","https://openalex.org/W2089917322","https://openalex.org/W2110798204","https://openalex.org/W2111284535","https://openalex.org/W2116456623","https://openalex.org/W2125234026","https://openalex.org/W2129070077","https://openalex.org/W2131342762","https://openalex.org/W2135431242","https://openalex.org/W2138243089","https://openalex.org/W2139759436","https://openalex.org/W2140262144","https://openalex.org/W2147768505","https://openalex.org/W2154887136","https://openalex.org/W2156387975","https://openalex.org/W2160815625","https://openalex.org/W2162931300","https://openalex.org/W2168231600","https://openalex.org/W2294059674","https://openalex.org/W2394932179","https://openalex.org/W2951781666","https://openalex.org/W2962820688","https://openalex.org/W6631362777","https://openalex.org/W6676481782","https://openalex.org/W6677681515","https://openalex.org/W6679097437","https://openalex.org/W6680418883","https://openalex.org/W6683965311","https://openalex.org/W6684859321"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W3008584592","https://openalex.org/W4380075502","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Recently,":[0],"maxout":[1,25,63],"networks":[2],"have":[3],"brought":[4],"significant":[5],"improvements":[6],"to":[7,90,113,153,157],"various":[8,46],"speech":[9],"recognition":[10],"and":[11,31,51,56,138,146],"computer":[12],"vision":[13],"tasks.":[14],"In":[15],"this":[16],"paper":[17],"we":[18,28,72,85],"introduce":[19],"two":[20],"new":[21],"types":[22],"of":[23,54,62,108,124],"generalized":[24],"units,":[26,137],"which":[27,99],"call":[29],"p-norm":[30,60,148],"soft-maxout.":[32],"We":[33],"investigate":[34],"their":[35],"performance":[36,123],"in":[37,45,68,111],"Large":[38],"Vocabulary":[39],"Continuous":[40],"Speech":[41],"Recognition":[42],"(LVCSR)":[43],"tasks":[44],"languages":[47],"with":[48,130,140,150],"10":[49],"hours":[50,53],"60":[52],"data,":[55],"find":[57],"that":[58,92,103],"the":[59,96,115],"generalization":[61],"consistently":[64],"performs":[65],"well.":[66],"Because,":[67],"our":[69,125,147],"training":[70,77,79],"setup,":[71],"sometimes":[73],"see":[74],"instability":[75],"during":[76],"when":[78],"unbounded-output":[80],"nonlinearities":[81,127],"such":[82],"as":[83],"these,":[84],"also":[86,139],"present":[87],"a":[88,101,141],"method":[89],"control":[91],"instability.":[93],"This":[94],"is":[95,100],"\u201cnormalization":[97],"layer\u201d,":[98],"nonlinearity":[102],"scales":[104],"down":[105],"all":[106],"dimensions":[107],"its":[109],"input":[110],"order":[112],"stop":[114],"average":[116],"squared":[117],"output":[118],"from":[119],"exceeding":[120],"one.":[121],"The":[122],"proposed":[126],"are":[128,155],"compared":[129],"maxout,":[131],"rectified":[132],"linear":[133],"units":[134,149],"(ReLU),":[135],"tanh":[136],"discriminatively":[142],"trained":[143],"SGMM/HMM":[144],"system,":[145],"p":[151],"equal":[152],"2":[154],"found":[156],"perform":[158],"best.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":36},{"year":2018,"cited_by_count":43},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":43},{"year":2015,"cited_by_count":41},{"year":2014,"cited_by_count":26}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}