{"id":"https://openalex.org/W2002052740","doi":"https://doi.org/10.1109/icassp.2013.6639141","title":"Investigation of deep Boltzmann machines for phone recognition","display_name":"Investigation of deep Boltzmann machines for phone recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2002052740","doi":"https://doi.org/10.1109/icassp.2013.6639141","mag":"2002052740"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5083126155","display_name":"You Zhao","orcid":"https://orcid.org/0000-0002-8305-5984"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao You","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036340946","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-6443-6298"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Interactive Digital Media Technol. Res. Center Inst. of Autom., Beijing, China","institution_ids":[]}]}],"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7600","last_page":"7603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/timit","display_name":"TIMIT","score":0.8541311621665955},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.8131961226463318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826889157295227},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7643616199493408},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.7608200311660767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6077845692634583},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5891247987747192},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5747849941253662},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.5653130412101746},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5503279566764832},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5418837666511536},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5357185006141663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4978911876678467},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4860546886920929},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47360944747924805},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4638962745666504},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43938297033309937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3870905637741089},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3572781980037689},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.31701213121414185}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8541311621665955},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.8131961226463318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826889157295227},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7643616199493408},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.7608200311660767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6077845692634583},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5891247987747192},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5747849941253662},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.5653130412101746},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5503279566764832},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5418837666511536},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5357185006141663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4978911876678467},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4860546886920929},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47360944747924805},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4638962745666504},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43938297033309937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3870905637741089},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3572781980037689},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31701213121414185},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W177847060","https://openalex.org/W189596042","https://openalex.org/W1904365287","https://openalex.org/W1993882792","https://openalex.org/W2071709160","https://openalex.org/W2076794394","https://openalex.org/W2077804127","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2144792281","https://openalex.org/W2154093685","https://openalex.org/W2394932179","https://openalex.org/W6607232846","https://openalex.org/W6607775107","https://openalex.org/W6640036494","https://openalex.org/W6680066585"],"related_works":["https://openalex.org/W2567271240","https://openalex.org/W3082895349","https://openalex.org/W3044458868","https://openalex.org/W1829305295","https://openalex.org/W3123344745","https://openalex.org/W1530536511","https://openalex.org/W2002052740","https://openalex.org/W2941846814","https://openalex.org/W3196362139","https://openalex.org/W2724953181"],"abstract_inverted_index":{"In":[0,65],"the":[1,27,32,35,41,54,60,81,90,103,110,116,127],"past":[2],"few":[3],"years,":[4],"deep":[5,18,72],"neural":[6],"networks":[7],"(DNNs)":[8],"achieved":[9],"great":[10],"successes":[11],"in":[12,45],"speech":[13],"recognition.":[14],"The":[15,50],"layer-wise":[16],"pre-trained":[17,61],"belief":[19],"network":[20],"(DBN)":[21],"is":[22,44,63,87,131],"known":[23],"as":[24],"one":[25,38],"of":[26,92,121],"critical":[28],"factor":[29],"to":[30,70,108],"optimize":[31],"DNN.":[33],"However,":[34],"DBN":[36,62],"has":[37,80],"shortcoming":[39],"that":[40,83],"pre-training":[42],"procedure":[43],"a":[46,84],"greedy":[47],"forward":[48],"pass.":[49],"top-down":[51,85],"influences":[52],"on":[53,76,102,126],"inference":[55],"process":[56],"are":[57,100],"ignored,":[58],"thus":[59],"suboptimal.":[64],"this":[66],"paper,":[67],"we":[68],"attempt":[69],"apply":[71],"Boltzmann":[73],"machine":[74],"(DBM)":[75],"acoustic":[77,112],"modeling.":[78],"DBM":[79],"advantages":[82],"feedback":[86],"incorporated":[88],"and":[89,136],"parameters":[91],"all":[93],"layers":[94],"can":[95],"be":[96],"jointly":[97],"optimized.":[98],"Experiments":[99],"conducted":[101],"TIMIT":[104],"phone":[105,123],"recognition":[106],"task":[107],"investigate":[109],"DBM-DNN":[111],"model.":[113],"Comparing":[114],"with":[115,118],"DBN-DNN":[117],"same":[119],"amount":[120],"parameters,":[122],"error":[124],"rate":[125],"core":[128],"test":[129],"set":[130],"reduced":[132],"by":[133,139],"3.8%":[134],"relatively,":[135],"additional":[137],"5.1%":[138],"dropout":[140],"fine-tuning.":[141]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}