{"id":"https://openalex.org/W2105099419","doi":"https://doi.org/10.1109/icassp.2012.6288833","title":"Auto-encoder bottleneck features using deep belief networks","display_name":"Auto-encoder bottleneck features using deep belief networks","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2105099419","doi":"https://doi.org/10.1109/icassp.2012.6288833","mag":"2105099419"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":182,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4153","last_page":"4156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/softmax-function","display_name":"Softmax function","score":0.8813256025314331},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8104883432388306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.684474527835846},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.564184308052063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5580219626426697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49800753593444824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4549446105957031},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.45154261589050293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4485458731651306},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44533565640449524},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.08150133490562439}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8813256025314331},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8104883432388306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.684474527835846},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.564184308052063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5580219626426697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49800753593444824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4549446105957031},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.45154261589050293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4485458731651306},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44533565640449524},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.08150133490562439},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1553004968","https://openalex.org/W1993561131","https://openalex.org/W2012897754","https://openalex.org/W2076794394","https://openalex.org/W2114016253","https://openalex.org/W2123237149","https://openalex.org/W2135346345","https://openalex.org/W2136922672","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2159948109","https://openalex.org/W2165712214","https://openalex.org/W2394932179","https://openalex.org/W6678292227","https://openalex.org/W6683644788","https://openalex.org/W6711962127"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2801655600","https://openalex.org/W2912971006"],"abstract_inverted_index":{"Neural":[0],"network":[1,67],"(NN)":[2],"bottleneck":[3,16,54],"(BN)":[4],"features":[5,126,163],"are":[6],"typically":[7],"created":[8],"by":[9,79],"training":[10],"a":[11,14,26,29,118,129,135,139,149,156,165,170,175,203],"NN":[12,27,145],"with":[13,28,105,138,148,174,182],"middle":[15],"layer.":[17],"Recently,":[18],"an":[19,49,190],"alternative":[20],"structure":[21],"was":[22],"proposed":[23],"which":[24],"trains":[25],"constant":[30],"number":[31],"of":[32,44,59,95,141,151,177,206],"hidden":[33],"units":[34],"to":[35,51,134],"predict":[36],"output":[37,46],"targets,":[38],"and":[39,110,143,186],"then":[40],"reduces":[41],"the":[42,61,64,72,83,86,93,106,124,183,198],"dimensionality":[43],"these":[45],"probabilities":[47],"through":[48],"auto-encoder,":[50],"create":[52],"auto-encoder":[53],"(AE-BN)":[55],"features.":[56,100,116],"The":[57],"benefit":[58],"placing":[60],"BN":[62,84],"after":[63],"posterior":[65],"estimation":[66],"is":[68],"that":[69,81,104],"it":[70],"avoids":[71],"loss":[73],"in":[74],"frame":[75],"classification":[76],"accuracy":[77],"incurred":[78],"networks":[80],"place":[82],"before":[85],"softmax.":[87],"In":[88,153],"this":[89],"work,":[90],"we":[91],"investigate":[92],"use":[94],"pre-training":[96],"when":[97],"creating":[98],"AE-BN":[99,107,115,125,162,187,199],"Our":[101],"experiments":[102],"indicate":[103],"architecture,":[108],"pre-trained":[109,144],"deeper":[111],"NNs":[112],"produce":[113],"better":[114],"On":[117],"50-hour":[119],"English":[120],"Broadcast":[121,159],"News":[122,160],"task,":[123,161],"provide":[127,164],"over":[128,169,197],"1%":[130],"absolute":[131,167,193],"improvement":[132,168],"compared":[133],"state-of-the-art":[136],"GMM/HMM":[137,172,184],"WER":[140,150,176,205],"18.8%":[142],"hybrid":[146],"system":[147,180,200],"18.4%.":[152],"addition,":[154],"on":[155,194],"larger":[157],"430-hour":[158],"0.5%":[166,192],"strong":[171],"baseline":[173,185],"16.0%.":[178],"Finally,":[179],"combination":[181],"systems":[188],"provides":[189],"additional":[191],"430":[195],"hours":[196],"alone,":[201],"yielding":[202],"final":[204],"15.0%.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"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":15},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}