{"id":"https://openalex.org/W2164361435","doi":"https://doi.org/10.1109/icassp.2012.6288869","title":"Factorial Hidden Restricted Boltzmann Machines for noise robust speech recognition","display_name":"Factorial Hidden Restricted Boltzmann Machines for noise robust speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2164361435","doi":"https://doi.org/10.1109/icassp.2012.6288869","mag":"2164361435"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288869","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":"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/A5088753951","display_name":"Steven J. Rennie","orcid":null},"institutions":[{"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":true,"raw_author_name":"Steven J. Rennie","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006171209","display_name":"Petr Fousek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149077","display_name":"IBM (Czechia)","ror":"https://ror.org/04dzqh472","country_code":"CZ","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210149077"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Fousek","raw_affiliation_strings":["IBM Czech Republic Limited, Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"IBM Czech Republic Limited, Prague, Czech Republic","institution_ids":["https://openalex.org/I4210149077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006329390","display_name":"Pierre Dognin","orcid":"https://orcid.org/0000-0001-5688-6005"},"institutions":[{"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":"Pierre L. Dognin","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088753951"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.2242,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83755464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4297","last_page":"4300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.996999979019165,"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/boltzmann-machine","display_name":"Boltzmann machine","score":0.7457227110862732},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.7386401891708374},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6964611411094666},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.6375153064727783},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6133326888084412},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6122809052467346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.60739666223526},{"id":"https://openalex.org/keywords/hidden-variable-theory","display_name":"Hidden variable theory","score":0.5265688896179199},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4924486577510834},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.49134793877601624},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.486621230840683},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45387688279151917},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45173391699790955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4417654275894165},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.43471580743789673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3267233669757843},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25736773014068604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2572018802165985}],"concepts":[{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.7457227110862732},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.7386401891708374},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6964611411094666},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.6375153064727783},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6133326888084412},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6122809052467346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.60739666223526},{"id":"https://openalex.org/C137002209","wikidata":"https://www.wikidata.org/wiki/Q898521","display_name":"Hidden variable theory","level":3,"score":0.5265688896179199},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4924486577510834},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.49134793877601624},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.486621230840683},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45387688279151917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45173391699790955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4417654275894165},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.43471580743789673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3267233669757843},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25736773014068604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2572018802165985},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288869","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":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W958726535","https://openalex.org/W2016077841","https://openalex.org/W2064082346","https://openalex.org/W2106714211","https://openalex.org/W2112089769","https://openalex.org/W2124914669","https://openalex.org/W2126597753","https://openalex.org/W2130322773","https://openalex.org/W2156744133","https://openalex.org/W6676877154","https://openalex.org/W6678801095","https://openalex.org/W6678958524"],"related_works":["https://openalex.org/W4283272532","https://openalex.org/W2952018105","https://openalex.org/W2916681395","https://openalex.org/W2119341610","https://openalex.org/W2556473569","https://openalex.org/W2193475944","https://openalex.org/W4302433642","https://openalex.org/W3185791989","https://openalex.org/W3141621448","https://openalex.org/W4287251628"],"abstract_inverted_index":{"We":[0,69],"present":[1],"the":[2,22,47,57,64,81,99,102,105,116,140],"Factorial":[3],"Hidden":[4],"Restricted":[5],"Boltzmann":[6],"Machine":[7],"(FHRBM)":[8],"for":[9,73],"robust":[10],"speech":[11,32,40,109,125],"recognition.":[12],"Speech":[13],"and":[14,21,33,110],"noise":[15,34,111,134],"are":[16,95,112],"modeled":[17,28],"as":[18],"independent":[19],"RBMs,":[20,45],"interaction":[23],"between":[24],"them":[25],"is":[26,53,59,142],"explicitly":[27],"to":[29,36,87,118,131],"capture":[30],"how":[31],"combine":[35],"generate":[37],"observed":[38],"noisy":[39,92,124],"features.":[41],"In":[42],"contrast":[43],"with":[44,63,80],"where":[46],"bottom":[48],"layer":[49],"of":[50,66,83,91,107,123],"random":[51],"variables":[52],"observed,":[54],"inference":[55,76],"in":[56],"FHRBM":[58,100],"intractable,":[60],"scaling":[61],"exponentially":[62],"number":[65,82],"hidden":[67,84],"units.":[68,85],"introduce":[70],"variational":[71],"algorithms":[72],"efficient":[74],"approximate":[75],"that":[77,104,127,139],"scale":[78],"linearly":[79],"Compared":[86],"traditional":[88],"factorial":[89],"models":[90],"speech,":[93],"which":[94],"based":[96],"on":[97],"GMMs,":[98],"has":[101],"advantage":[103],"representations":[106],"both":[108],"highly":[113],"distributed,":[114],"allowing":[115],"model":[117],"learn":[119],"a":[120],"parts-based":[121],"representation":[122],"data":[126],"can":[128],"generalize":[129],"better":[130],"previously":[132],"unseen":[133],"compositions.":[135],"Preliminary":[136],"results":[137],"suggest":[138],"approach":[141],"promising.":[143]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}