{"id":"https://openalex.org/W1995562189","doi":"https://doi.org/10.1109/taslp.2014.2339736","title":"Convolutional Neural Networks for Speech Recognition","display_name":"Convolutional Neural Networks for Speech Recognition","publication_year":2014,"publication_date":"2014-07-16","ids":{"openalex":"https://openalex.org/W1995562189","doi":"https://doi.org/10.1109/taslp.2014.2339736","mag":"1995562189"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2339736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2339736","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":false,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, York University, Toronto, ON, Canada","[Department of Electrical Engineering and Computer Science, Lassonde school of Engineering, York University, Toronto, ON, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"[Department of Electrical Engineering and Computer Science, Lassonde school of Engineering, York University, Toronto, ON, Canada]","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","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":["Computer Science Department, University of Toronto, Toronto, ON, Canada","[Computer Science Department, University of Toronto, Toronto, ON, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"[Computer Science Department, University of Toronto, Toronto, ON, Canada]","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"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":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, York University, Toronto, ON, Canada","[Department of Electrical Engineering and Computer Science, Lassonde school of Engineering, York University, Toronto, ON, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"[Department of Electrical Engineering and Computer Science, Lassonde school of Engineering, York University, Toronto, ON, 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","Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","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":["Computer Science Department, University of Toronto, Toronto, ON, Canada","[Computer Science Department, University of Toronto, Toronto, ON, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"[Computer Science Department, University of Toronto, Toronto, ON, Canada]","institution_ids":["https://openalex.org/I185261750"]}]},{"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","Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":125.9109,"has_fulltext":false,"cited_by_count":2286,"citation_normalized_percentile":{"value":0.99977072,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"22","issue":"10","first_page":"1533","last_page":"1545"},"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":0.9993000030517578,"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":0.9987999796867371,"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":0.8328655958175659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7773353457450867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7643765211105347},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6983302235603333},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6971725225448608},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6432108879089355},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6430885195732117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45803144574165344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4517001509666443},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4430463910102844},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4144965410232544}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8328655958175659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773353457450867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7643765211105347},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6983302235603333},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6971725225448608},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6432108879089355},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6430885195732117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45803144574165344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4517001509666443},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4430463910102844},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4144965410232544},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2014.2339736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2339736","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W1499864241","https://openalex.org/W1523493493","https://openalex.org/W1536929369","https://openalex.org/W1538131130","https://openalex.org/W1553004968","https://openalex.org/W1860566644","https://openalex.org/W1993882792","https://openalex.org/W2012897754","https://openalex.org/W2013598660","https://openalex.org/W2016084804","https://openalex.org/W2020144989","https://openalex.org/W2022011789","https://openalex.org/W2024539680","https://openalex.org/W2036242736","https://openalex.org/W2063689849","https://openalex.org/W2074079435","https://openalex.org/W2076794394","https://openalex.org/W2077804127","https://openalex.org/W2091432990","https://openalex.org/W2101926813","https://openalex.org/W2103359087","https://openalex.org/W2106051978","https://openalex.org/W2107789863","https://openalex.org/W2112739286","https://openalex.org/W2116064496","https://openalex.org/W2117671523","https://openalex.org/W2125964738","https://openalex.org/W2130325614","https://openalex.org/W2141778357","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2149600041","https://openalex.org/W2155273149","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2161742217","https://openalex.org/W2165712214","https://openalex.org/W2168013545","https://openalex.org/W2172097686","https://openalex.org/W2188183693","https://openalex.org/W2213952365","https://openalex.org/W2394932179","https://openalex.org/W2964138484","https://openalex.org/W6608710415","https://openalex.org/W6631319189","https://openalex.org/W6675321185","https://openalex.org/W6676071220","https://openalex.org/W6688428952"],"related_works":["https://openalex.org/W2501000458","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W2148099973","https://openalex.org/W1990589093","https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2150890698","https://openalex.org/W1578749070","https://openalex.org/W2005708641"],"abstract_inverted_index":{"Recently,":[0],"the":[1,20,33,36,71,121,140,149,154],"hybrid":[2],"deep":[3],"neural":[4,61],"network":[5],"(DNN)-hidden":[6],"Markov":[7],"model":[8,24,39,93],"(HMM)":[9],"has":[10],"been":[11],"shown":[12],"to":[13,32,38,114,127],"significantly":[14],"improve":[15],"speech":[16,43,82,94,118,159],"recognition":[17,152,160],"performance":[18,27],"over":[19],"conventional":[21],"Gaussian":[22],"mixture":[23],"(GMM)-HMM.":[25],"The":[26,96],"improvement":[28],"is":[29,125],"partially":[30],"attributed":[31],"ability":[34],"of":[35,70,112,117],"DNN":[37],"complex":[40],"correlations":[41],"in":[42,107],"features.":[44,95],"In":[45],"this":[46],"paper,":[47],"we":[48],"show":[49,136],"that":[50,90,137],"further":[51,85],"error":[52,141],"rate":[53,142],"reduction":[54],"can":[55,78,91],"be":[56,79],"obtained":[57],"by":[58,143],"using":[59],"convolutional":[60],"networks":[62],"(CNNs).":[63],"We":[64,84],"first":[65],"present":[66],"a":[67,87],"concise":[68],"description":[69],"basic":[72],"CNN":[73],"and":[74,105,131,153],"explain":[75],"how":[76],"it":[77],"used":[80],"for":[81],"recognition.":[83],"propose":[86],"limited-weight-sharing":[88],"scheme":[89],"better":[92],"special":[97],"structure":[98],"such":[99],"as":[100],"local":[101],"connectivity,":[102],"weight":[103],"sharing,":[104],"pooling":[106],"CNNs":[108,138],"exhibits":[109],"some":[110],"degree":[111],"invariance":[113],"small":[115],"shifts":[116],"features":[119],"along":[120],"frequency":[122],"axis,":[123],"which":[124],"important":[126],"deal":[128],"with":[129,146],"speaker":[130],"environment":[132],"variations.":[133],"Experimental":[134],"results":[135],"reduce":[139],"6%-10%":[144],"compared":[145],"DNNs":[147],"on":[148],"TIMIT":[150],"phone":[151],"voice":[155],"search":[156],"large":[157],"vocabulary":[158],"tasks.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":33},{"year":2025,"cited_by_count":121},{"year":2024,"cited_by_count":183},{"year":2023,"cited_by_count":240},{"year":2022,"cited_by_count":248},{"year":2021,"cited_by_count":297},{"year":2020,"cited_by_count":312},{"year":2019,"cited_by_count":302},{"year":2018,"cited_by_count":245},{"year":2017,"cited_by_count":167},{"year":2016,"cited_by_count":89},{"year":2015,"cited_by_count":46},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}