{"id":"https://openalex.org/W2198724430","doi":"https://doi.org/10.1109/icassp.2016.7472620","title":"Very deep multilingual convolutional neural networks for LVCSR","display_name":"Very deep multilingual convolutional neural networks for LVCSR","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2198724430","doi":"https://doi.org/10.1109/icassp.2016.7472620","mag":"2198724430"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5006044037","display_name":"Tom Sercu","orcid":"https://orcid.org/0000-0003-2947-6064"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Sercu","raw_affiliation_strings":["Center for Data Science, New York University","IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029859679","display_name":"Christian Puhrsch","orcid":"https://orcid.org/0009-0002-3925-967X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Puhrsch","raw_affiliation_strings":["Center for Data Science, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, U.S.A","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yann LeCun","raw_affiliation_strings":["Center for Data Science, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":215,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4955","last_page":"4959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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":0.8880850672721863},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6769588589668274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5914312601089478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.581204891204834},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5496665835380554},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5399160385131836},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5187037587165833},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5124748349189758},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4477812349796295},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4365488588809967},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3469558358192444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8880850672721863},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6769588589668274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914312601089478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.581204891204834},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5496665835380554},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5399160385131836},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5187037587165833},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5124748349189758},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4477812349796295},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4365488588809967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3469558358192444},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W162588823","https://openalex.org/W281811447","https://openalex.org/W1501286448","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W1975550806","https://openalex.org/W1992912377","https://openalex.org/W2022508996","https://openalex.org/W2028706510","https://openalex.org/W2102605133","https://openalex.org/W2106051978","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2114016253","https://openalex.org/W2117671523","https://openalex.org/W2125085157","https://openalex.org/W2127982613","https://openalex.org/W2148099973","https://openalex.org/W2155273149","https://openalex.org/W2162741153","https://openalex.org/W2162794177","https://openalex.org/W2163605009","https://openalex.org/W2171740948","https://openalex.org/W2394932179","https://openalex.org/W2395611524","https://openalex.org/W2397947827","https://openalex.org/W2951234442","https://openalex.org/W2962835968","https://openalex.org/W2963217176","https://openalex.org/W2963490782","https://openalex.org/W2963542991","https://openalex.org/W2964121744","https://openalex.org/W6600284362","https://openalex.org/W6629368666","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6639288305","https://openalex.org/W6640054144","https://openalex.org/W6684191040","https://openalex.org/W6685261749","https://openalex.org/W6712816420"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W4401096132"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,35],"networks":[2,36],"(CNNs)":[3],"are":[4,70],"a":[5,45,57,119,170,179],"standard":[6],"component":[7],"of":[8,47,146,165,174],"many":[9],"current":[10],"state-of-the-art":[11],"Large":[12],"Vocabulary":[13],"Continuous":[14],"Speech":[15],"Recognition":[16],"(LVCSR)":[17],"systems.":[18],"However,":[19],"CNNs":[20,51,93,156],"in":[21,30,50],"LVCSR":[22],"have":[23],"not":[24],"kept":[25],"pace":[26],"with":[27,63,78,94],"recent":[28],"advances":[29,49],"other":[31],"domains":[32],"where":[33],"deeper":[34],"provide":[37],"superior":[38],"performance.":[39],"In":[40],"this":[41],"paper":[42],"we":[43,55,90,99],"propose":[44],"number":[46],"architectural":[48],"for":[52,122],"LVCSR.":[53],"First,":[54],"introduce":[56,91,100],"very":[58,154],"deep":[59,155],"convolutional":[60,72],"network":[61],"architecture":[62],"up":[64],"to":[65],"14":[66],"weight":[67],"layers.":[68,97],"There":[69],"multiple":[71,95],"layers":[73],"before":[74],"each":[75],"pooling":[76],"layer,":[77],"small":[79],"3\u00d73":[80],"kernels,":[81],"inspired":[82],"by":[83,138],"the":[84,115,134,143,153,158,162,186],"VGG":[85],"Imagenet":[86],"2014":[87],"architecture.":[88],"Then,":[89],"multilingual":[92],"untied":[96],"Finally,":[98],"multi-scale":[101],"input":[102],"features":[103],"aimed":[104],"at":[105,109],"exploiting":[106],"more":[107],"context":[108],"negligible":[110],"computational":[111],"cost.":[112],"We":[113,150],"evaluate":[114,152],"improvements":[116],"first":[117],"on":[118,142,157],"Babel":[120],"task":[121],"low":[123],"resource":[124],"speech":[125],"recognition,":[126],"obtaining":[127],"an":[128],"absolute":[129],"5.77%":[130],"WER":[131,181],"improvement":[132,182],"over":[133,185],"baseline":[135],"PLP":[136],"DNN":[137],"training":[139,167],"our":[140],"CNN":[141,189],"combined":[144],"data":[145],"six":[147],"different":[148],"languages.":[149],"then":[151],"Hub5'00":[159],"benchmark":[160],"(using":[161],"262":[163],"hours":[164],"SWB-1":[166],"data)":[168],"achieving":[169],"word":[171],"error":[172],"rate":[173],"11.8%":[175],"after":[176],"cross-entropy":[177],"training,":[178],"1.4%":[180],"(10.6%":[183],"relative)":[184],"best":[187],"published":[188],"result":[190],"so":[191],"far.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":45},{"year":2017,"cited_by_count":45},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}