{"id":"https://openalex.org/W2112739286","doi":"https://doi.org/10.1109/icassp.2013.6639347","title":"Deep convolutional neural networks for LVCSR","display_name":"Deep convolutional neural networks for LVCSR","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2112739286","doi":"https://doi.org/10.1109/icassp.2013.6639347","mag":"2112739286"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639347","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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"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":["Department of Computer Science, University of Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1072,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8614","last_page":"8618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9941999912261963,"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":0.8378672003746033},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8008013963699341},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7689352035522461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.636144757270813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6047349572181702},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5726492404937744},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5560570359230042},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5557808876037598},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5278865098953247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4615021347999573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45672258734703064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378672003746033},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8008013963699341},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7689352035522461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.636144757270813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6047349572181702},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5726492404937744},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5560570359230042},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5557808876037598},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5278865098953247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4615021347999573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45672258734703064},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639347","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.753.6656","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.753.6656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1309.1501.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1538131130","https://openalex.org/W2076794394","https://openalex.org/W2105099419","https://openalex.org/W2112796928","https://openalex.org/W2114016253","https://openalex.org/W2134557905","https://openalex.org/W2144354855","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2155117693","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2504108613","https://openalex.org/W6632100814"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W803346624","https://openalex.org/W2152352598","https://openalex.org/W2810679507"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1,46],"Networks":[2,47],"(CNNs)":[3],"are":[4,36,85],"an":[5],"alternative":[6],"type":[7,106],"of":[8,32,92,114,124],"neural":[9,115],"network":[10,116],"that":[11,135],"can":[12],"be":[13],"used":[14],"to":[15,44,56,67,72,129],"reduce":[16],"spectral":[17,21],"variations":[18],"and":[19,101,131,145,157],"model":[20,40],"correlations":[22],"which":[23],"exist":[24],"in":[25],"signals.":[26],"Since":[27],"speech":[28,42,59],"signals":[29],"exhibit":[30],"both":[31],"these":[33],"properties,":[34],"CNNs":[35,55,69,120,128,136],"a":[37,122,139,146,153],"more":[38],"effective":[39,70],"for":[41,74,107],"compared":[43,71],"Deep":[45],"(DNNs).":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,62,78],"explore":[53,111],"applying":[54],"large":[57],"vocabulary":[58],"tasks.":[60,76],"First,":[61],"determine":[63],"the":[64,89,97,102,112],"appropriate":[65],"architecture":[66],"make":[68],"DNNs":[73,130],"LVCSR":[75,125],"Specifically,":[77],"focus":[79],"on":[80,121,152],"how":[81],"many":[82],"convolutional":[83],"layers":[84],"needed,":[86],"what":[87,95],"is":[88,96],"optimal":[90],"number":[91],"hidden":[93],"units,":[94],"best":[98,103],"pooling":[99],"strategy,":[100],"input":[104],"feature":[105],"CNNs.":[108],"We":[109,133],"then":[110],"behavior":[113],"features":[117],"extracted":[118],"from":[119],"variety":[123],"tasks,":[126],"comparing":[127],"GMMs.":[132],"find":[134],"offer":[137],"between":[138],"13-30%":[140],"relative":[141,148],"improvement":[142,149],"over":[143,150],"GMMs,":[144],"4-12%":[147],"DNNs,":[151],"400-hr":[154],"Broadcast":[155],"News":[156],"300-hr":[158],"Switchboard":[159],"task.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":82},{"year":2021,"cited_by_count":135},{"year":2020,"cited_by_count":167},{"year":2019,"cited_by_count":139},{"year":2018,"cited_by_count":125},{"year":2017,"cited_by_count":119},{"year":2016,"cited_by_count":95},{"year":2015,"cited_by_count":67},{"year":2014,"cited_by_count":45},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}