{"id":"https://openalex.org/W2172097686","doi":"https://doi.org/10.1109/icassp.2012.6288863","title":"Understanding how Deep Belief Networks perform acoustic modelling","display_name":"Understanding how Deep Belief Networks perform acoustic modelling","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2172097686","doi":"https://doi.org/10.1109/icassp.2012.6288863","mag":"2172097686"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288863","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/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdel-rahman Mohamed","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Geoffrey Hinton","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052428595","display_name":"Gerald Penn","orcid":"https://orcid.org/0000-0003-3553-8305"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gerald Penn","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":270,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4273","last_page":"4276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/deep-belief-network","display_name":"Deep belief network","score":0.872029185295105},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7993347644805908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7351555824279785},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7099261283874512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6544604897499084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.561960756778717},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5481758713722229},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5395175218582153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4912669062614441},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4763358235359192},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4543655216693878},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44483819603919983},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4344835579395294}],"concepts":[{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.872029185295105},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7993347644805908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351555824279785},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7099261283874512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6544604897499084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.561960756778717},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5481758713722229},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5395175218582153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4912669062614441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4763358235359192},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4543655216693878},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44483819603919983},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4344835579395294},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288863","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.2314","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.2314","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/%7Easamir/papers/icassp12_dbn.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1553004968","https://openalex.org/W1993882792","https://openalex.org/W2076794394","https://openalex.org/W2102512139","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2165712214","https://openalex.org/W2187089797","https://openalex.org/W2377164795"],"related_works":["https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2148099973","https://openalex.org/W2172097686","https://openalex.org/W2002052740","https://openalex.org/W2340308015"],"abstract_inverted_index":{"Deep":[0],"Belief":[1],"Networks":[2],"(DBNs)":[3],"are":[4,31,51,111],"a":[5,17,80,124],"very":[6],"competitive":[7,32],"alternative":[8],"to":[9,21,64,114],"Gaussian":[10],"mixture":[11],"models":[12],"for":[13,33,123],"relating":[14],"states":[15],"of":[16,23,59,84,100,120],"hidden":[18,47],"Markov":[19],"model":[20],"frames":[22],"coefficients":[24],"derived":[25],"from":[26],"the":[27,65,76,85,88,93,97,101,116],"acoustic":[28],"input.":[29],"They":[30],"three":[34,61],"reasons:":[35],"DBNs":[36,43,50,94],"can":[37],"be":[38],"fine-tuned":[39],"as":[40],"neural":[41],"networks;":[42],"have":[44],"many":[45],"non-linear":[46],"layers;":[48],"and":[49,79],"generatively":[52],"pre-trained.":[53],"This":[54],"paper":[55],"illustrates":[56],"how":[57],"each":[58],"these":[60],"aspects":[62],"contributes":[63],"DBN's":[66],"good":[67],"recognition":[68,73],"performance":[69,74],"using":[70],"both":[71],"phone":[72],"on":[75],"TIMIT":[77],"corpus":[78],"dimensionally":[81],"reduced":[82],"visualization":[83],"relationships":[86],"between":[87],"feature":[89,102],"vectors":[90,103],"learned":[91],"by":[92],"that":[95],"preserves":[96],"similarity":[98],"structure":[99],"at":[104],"multiple":[105],"scales.":[106],"The":[107],"same":[108],"two":[109],"methods":[110],"also":[112],"used":[113],"investigate":[115],"most":[117],"suitable":[118],"type":[119],"input":[121],"representation":[122],"DBN.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":29},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":30},{"year":2014,"cited_by_count":32},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}