{"id":"https://openalex.org/W2106051978","doi":"https://doi.org/10.1109/icassp.2011.5947494","title":"Deep Belief Networks using discriminative features for phone recognition","display_name":"Deep Belief Networks using discriminative features for phone recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2106051978","doi":"https://doi.org/10.1109/icassp.2011.5947494","mag":"2106051978"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdel-rahman Mohamed","raw_affiliation_strings":["Department of Computer Science, University of Toronto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, USA","institution_ids":[]}]},{"author_position":"middle","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":[]},{"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/A5047062711","display_name":"George E. Dahl","orcid":"https://orcid.org/0000-0002-0083-844X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Dahl","raw_affiliation_strings":["Department of Computer Science, University of Toronto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, USA","institution_ids":[]}]},{"author_position":"middle","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":[]},{"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/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geoffrey E. Hinton","raw_affiliation_strings":["Department of Computer Science, University of Toronto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael A. Picheny","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":[]},{"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":292,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5060","last_page":"5063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9915000200271606,"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/discriminative-model","display_name":"Discriminative model","score":0.8428375124931335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713929295539856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.579434335231781},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49401384592056274},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4644581973552704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.417793333530426},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.4177316427230835},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3157825469970703}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8428375124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713929295539856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579434335231781},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49401384592056274},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4644581973552704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.417793333530426},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.4177316427230835},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3157825469970703},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.220.4013","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.4013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/%7Ehinton/absps/speechDBNdiscrim.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W88081813","https://openalex.org/W1553004968","https://openalex.org/W1993882792","https://openalex.org/W1994197834","https://openalex.org/W2002342963","https://openalex.org/W2077804127","https://openalex.org/W2103359087","https://openalex.org/W2116064496","https://openalex.org/W2118595744","https://openalex.org/W2125234026","https://openalex.org/W2136922672","https://openalex.org/W2138857742","https://openalex.org/W2155117693","https://openalex.org/W2158289097","https://openalex.org/W2165119652","https://openalex.org/W2606321545","https://openalex.org/W6675321185","https://openalex.org/W6680300913"],"related_works":["https://openalex.org/W2594876342","https://openalex.org/W2585432886","https://openalex.org/W2165991108","https://openalex.org/W3082895349","https://openalex.org/W2565516711","https://openalex.org/W3004069267","https://openalex.org/W3127162800","https://openalex.org/W2061937230","https://openalex.org/W4327774331","https://openalex.org/W3136021864"],"abstract_inverted_index":{"Deep":[0],"Belief":[1],"Networks":[2],"(DBNs)":[3],"are":[4,71,101,119],"multi-layer":[5],"generative":[6],"models.":[7],"They":[8],"can":[9,38],"be":[10,39],"trained":[11,54],"to":[12,41,55],"model":[13,143],"windows":[14],"of":[15,25,33,46,64,134],"coefficients":[16,99],"extracted":[17],"from":[18],"speech":[19,75],"and":[20,139,144,149],"they":[21,112,129],"discover":[22],"multiple":[23],"layers":[24],"features":[26,37,69],"that":[27,51,70,100,111],"capture":[28],"the":[29,34,43,57,61,65,77,125],"higher-order":[30],"statistical":[31],"structure":[32],"data.":[35],"These":[36],"used":[40,92],"initialize":[42],"hidden":[44],"units":[45],"a":[47,140,150],"feed-forward":[48],"neural":[49,78],"network":[50,79],"is":[52],"then":[53],"predict":[56],"HMM":[58],"state":[59],"for":[60,94],"central":[62],"frame":[63],"window.":[66],"Initializing":[67],"with":[68,85,97],"good":[72],"at":[73],"generating":[74],"makes":[76],"perform":[80],"much":[81],"better":[82,115],"than":[83],"initializing":[84],"random":[86],"weights.":[87],"DBNs":[88],"have":[89],"already":[90],"been":[91],"successfully":[93],"phone":[95,131],"recognition":[96],"input":[98],"MFCCs":[102],"or":[103],"filterbank":[104],"outputs.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109],"demonstrate":[110],"work":[113],"even":[114],"when":[116],"their":[117],"inputs":[118],"speaker":[120],"adaptive,":[121],"discriminative":[122],"features.":[123],"On":[124],"standard":[126],"TIMIT":[127],"corpus,":[128],"give":[130],"error":[132],"rates":[133],"19.6%":[135],"using":[136,146],"monophone":[137,147],"HMMs":[138,148],"bigram":[141],"language":[142,152],"19.4%":[145],"trigram":[151],"model.":[153]},"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":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":50},{"year":2015,"cited_by_count":35},{"year":2014,"cited_by_count":38},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}