{"id":"https://openalex.org/W2188183693","doi":"https://doi.org/10.21437/interspeech.2013-744","title":"Exploring convolutional neural network structures and optimization techniques for speech recognition","display_name":"Exploring convolutional neural network structures and optimization techniques for speech recognition","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2188183693","doi":"https://doi.org/10.21437/interspeech.2013-744","mag":"2188183693"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-744","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":["Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research, Redmond, WA USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft Research, Redmond, WA USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077733105"],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":44.0004,"has_fulltext":false,"cited_by_count":387,"citation_normalized_percentile":{"value":0.99833657,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3366","last_page":"3370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7889308333396912},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7195622324943542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5600879192352295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4623253643512726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45396551489830017},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.433646023273468},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.41718846559524536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889308333396912},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7195622324943542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5600879192352295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4623253643512726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45396551489830017},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.433646023273468},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.41718846559524536}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-744","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.648","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.yorku.ca/%7Eossama/pub/cnn_2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1538131130","https://openalex.org/W1984541135","https://openalex.org/W1993882792","https://openalex.org/W2036242736","https://openalex.org/W2076794394","https://openalex.org/W2077804127","https://openalex.org/W2095168618","https://openalex.org/W2107789863","https://openalex.org/W2112796928","https://openalex.org/W2130325614","https://openalex.org/W2134557905","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2162871885","https://openalex.org/W2394932179"],"related_works":["https://openalex.org/W2578422401","https://openalex.org/W1584270863","https://openalex.org/W1595652908","https://openalex.org/W2603525251","https://openalex.org/W4285294654","https://openalex.org/W2085961337","https://openalex.org/W2950022897","https://openalex.org/W2890297197","https://openalex.org/W2386241395","https://openalex.org/W2357447513"],"abstract_inverted_index":{"Recently,":[0],"convolutional":[1,111],"neural":[2,21],"networks":[3,16],"(CNNs)":[4],"have":[5,123],"been":[6],"shown":[7],"to":[8],"outperform":[9,125],"the":[10,18,30,39,44,87,90,100,114,126,131,135,154,167,171],"standard":[11],"fully":[12],"connected":[13],"deep":[14,20],"neu-ral":[15],"within":[17],"hybrid":[19],"network":[22],"/":[23],"hidden":[24],"Markov":[25],"model":[26],"(DNN/HMM)":[27],"framework":[28],"on":[29,133,193],"phone":[31,136],"recogni-tion":[32],"task.":[33,199],"In":[34],"this":[35],"paper,":[36],"we":[37,98,122,184],"extend":[38],"earlier":[40,127],"basic":[41,128],"form":[42,129],"of":[43,72,102,113,130],"CNN":[45,56,103,120,169,187],"and":[46,60,67,70,138,176],"explore":[47],"it":[48],"in":[49,89],"multiple":[50],"ways.":[51],"We":[52,76,116],"first":[53],"investigate":[54],"sev-eral":[55],"architectures,":[57],"including":[58],"full":[59,155],"limited":[61,147],"weight":[62,148,156],"shar-ing,":[63],"convolution":[64,74],"along":[65],"frequency":[66],"time":[68],"axes,":[69],"stacking":[71],"several":[73],"layers.":[75],"then":[77],"develop":[78],"a":[79,110,178,194],"novel":[80],"weighted":[81],"softmax":[82,160],"pooling":[83,91,161],"layer":[84,92,162],"so":[85],"that":[86,118,186],"size":[88],"can":[93],"be":[94],"automatically":[95],"learned.":[96],"Further,":[97],"evaluate":[99],"effect":[101],"pretraining,":[104],"which":[105],"is":[106],"achieved":[107],"by":[108],"using":[109],"version":[112],"RBM.":[115],"show":[117,185],"all":[119],"architectures":[121],"in-vestigated":[124],"DNN":[132],"both":[134],"recognition":[137,198],"large":[139,195],"vocabulary":[140,196],"speech":[141,197],"recog-nition":[142],"tasks.":[143],"The":[144,159],"architecture":[145],"with":[146,170],"sharing":[149,157],"pro-vides":[150],"additional":[151],"gains":[152],"over":[153],"architecture.":[158],"performs":[163],"as":[164,166],"well":[165],"best":[168],"manually":[172],"tuned":[173],"fixed-pooling":[174],"size,":[175],"has":[177],"potential":[179],"for":[180],"further":[181],"improvement.":[182],"Finally,":[183],"pretrain-ing":[188],"produces":[189],"significantly":[190],"better":[191],"results":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":48},{"year":2017,"cited_by_count":58},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":30},{"year":2014,"cited_by_count":22},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}