{"id":"https://openalex.org/W2132037657","doi":"https://doi.org/10.1109/icassp.2011.5947700","title":"Learning a better representation of speech soundwaves using restricted boltzmann machines","display_name":"Learning a better representation of speech soundwaves using restricted boltzmann machines","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2132037657","doi":"https://doi.org/10.1109/icassp.2011.5947700","mag":"2132037657"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947700","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/A5112445699","display_name":"Navdeep Jaitly","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":"Navdeep Jaitly","raw_affiliation_strings":["Department of Computer Science, University of Toronto, M5S 3G4, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, M5S 3G4, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","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, M5S 3G4, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, M5S 3G4, 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":229,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5884","last_page":"5887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T10320","display_name":"Neural Networks and Applications","score":0.998199999332428,"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":0.9968000054359436,"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/cepstrum","display_name":"Cepstrum","score":0.7925803065299988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7515931129455566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479761838912964},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6471889019012451},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.6152188181877136},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.5963596701622009},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.5703731775283813},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5232438445091248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4493166506290436},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.40695035457611084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3230098485946655},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28255563974380493},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.25289684534072876}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7925803065299988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7515931129455566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479761838912964},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6471889019012451},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.6152188181877136},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.5963596701622009},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.5703731775283813},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5232438445091248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4493166506290436},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.40695035457611084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3230098485946655},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28255563974380493},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25289684534072876},{"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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947700","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:10.1.1.220.3847","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.3847","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/jaitly_ICASSP2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"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":22,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W137106866","https://openalex.org/W1562289873","https://openalex.org/W1647054946","https://openalex.org/W1665214252","https://openalex.org/W1813659000","https://openalex.org/W2000232298","https://openalex.org/W2014641584","https://openalex.org/W2017399882","https://openalex.org/W2089693651","https://openalex.org/W2103359087","https://openalex.org/W2104997912","https://openalex.org/W2107789863","https://openalex.org/W2108384452","https://openalex.org/W2110871230","https://openalex.org/W2116064496","https://openalex.org/W2131700150","https://openalex.org/W2136163184","https://openalex.org/W2978329087","https://openalex.org/W6605498254","https://openalex.org/W6637242042","https://openalex.org/W6638304892"],"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/W2529583158","https://openalex.org/W2551541394","https://openalex.org/W2140099343"],"abstract_inverted_index":{"State":[0],"of":[1,89,116],"the":[2,86,90,130],"art":[3],"speech":[4,10,25,39,81,103],"recognition":[5,40,74,126],"systems":[6],"rely":[7],"on":[8,136],"preprocessed":[9],"features":[11],"such":[12,42],"as":[13],"Mel":[14,137],"cepstrum":[15,138],"or":[16],"linear":[17],"predictive":[18],"coding":[19],"coefficients":[20],"that":[21,58],"collapse":[22],"high":[23],"dimensional":[24,30,44,67],"sound":[26,91,104],"waves":[27,105],"into":[28],"low":[29,43],"encodings.":[31],"While":[32],"these":[33],"have":[34],"been":[35],"successfully":[36],"applied":[37,79],"in":[38,55,73],"systems,":[41],"encodings":[45,68],"may":[46],"lose":[47],"some":[48],"relevant":[49],"information":[50,54],"and":[51,76,119],"express":[52],"other":[53],"a":[56,98,107,113],"way":[57],"makes":[59],"it":[60],"difficult":[61],"to":[62,80],"use":[63],"for":[64,101,133],"discrimination.":[65],"Higher":[66],"could":[69],"both":[70],"improve":[71],"performance":[72,127],"tasks,":[75],"also":[77],"be":[78],"synthesis":[82],"by":[83],"better":[84,128],"modeling":[85,102],"statistical":[87],"structure":[88],"waves.":[92],"In":[93],"this":[94],"paper":[95],"we":[96,120],"present":[97],"novel":[99,114],"approach":[100],"using":[106],"Restricted":[108],"Boltzmann":[109],"machine":[110],"(RBM)":[111],"with":[112],"type":[115],"hidden":[117],"variable":[118],"report":[121],"initial":[122],"results":[123],"demonstrating":[124],"phoneme":[125],"than":[129],"current":[131],"state-of-the-art":[132],"methods":[134],"based":[135],"coefficients.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}