{"id":"https://openalex.org/W2587717635","doi":"https://doi.org/10.1109/slt.2016.7846307","title":"Very deep convolutional neural networks for robust speech recognition","display_name":"Very deep convolutional neural networks for robust speech recognition","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2587717635","doi":"https://doi.org/10.1109/slt.2016.7846307","mag":"2587717635"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","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/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Cambridge University Engineering Department, Cambridge, UK","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C Woodland","raw_affiliation_strings":["Cambridge University Engineering Department, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100341993"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":14.7225,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98882437,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"488"},"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":0.9969000220298767,"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":0.8180537819862366},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.74249666929245},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.720344603061676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6686427593231201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6578055024147034},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6164860725402832},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6047846674919128},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5965263247489929},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5890687108039856},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5815925002098083},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5719727873802185},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.48126503825187683},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.43743225932121277},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.43028154969215393},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24888473749160767},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1829935908317566},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.057588934898376465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8180537819862366},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.74249666929245},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.720344603061676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6686427593231201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6578055024147034},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6164860725402832},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6047846674919128},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5965263247489929},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5890687108039856},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5815925002098083},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5719727873802185},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.48126503825187683},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.43743225932121277},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.43028154969215393},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24888473749160767},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1829935908317566},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.057588934898376465},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/slt.2016.7846307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1976637928","https://openalex.org/W1992475611","https://openalex.org/W2020408662","https://openalex.org/W2028706510","https://openalex.org/W2033310064","https://openalex.org/W2062164080","https://openalex.org/W2097117768","https://openalex.org/W2112739286","https://openalex.org/W2115086266","https://openalex.org/W2131342762","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2239847623","https://openalex.org/W2288402171","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2397042577","https://openalex.org/W2397947827","https://openalex.org/W2401430117","https://openalex.org/W2402922286","https://openalex.org/W2406264770","https://openalex.org/W2407023693","https://openalex.org/W2408583661","https://openalex.org/W2491899193","https://openalex.org/W2950179405","https://openalex.org/W2962835968","https://openalex.org/W2963574257","https://openalex.org/W3125118953","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6639736908","https://openalex.org/W6674914833","https://openalex.org/W6677416784","https://openalex.org/W6696982659","https://openalex.org/W6714171909"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W4387022695"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,25,35,38,49,112,119,152,156],"extension":[4],"and":[5,42,51,56,74,98,130,172],"optimisation":[6],"of":[7,21,32,37,58,90,163],"our":[8],"previous":[9],"work":[10],"on":[11],"very":[12,91,120,149,157],"deep":[13,92,121,158],"convolutional":[14,33,68],"neural":[15],"networks":[16],"(CNNs)":[17],"for":[18],"effective":[19],"recognition":[20],"noisy":[22],"speech":[23],"in":[24,141],"Aurora":[26,153],"4":[27,154],"task.":[28],"The":[29],"appropriate":[30,71],"number":[31],"layers,":[34],"sizes":[36,53],"filters,":[39],"pooling":[40,52],"operations":[41],"input":[43,59,72,75],"feature":[44,60,76,169],"maps":[45,61],"are":[46,54,62,80],"all":[47],"modified:":[48],"filter":[50],"reduced":[55],"dimensions":[57],"extended":[63],"to":[64],"allow":[65],"adding":[66],"more":[67],"layers.":[69],"Furthermore":[70],"padding":[73],"map":[77],"selection":[78],"strategies":[79],"developed.":[81,102],"In":[82],"addition,":[83],"an":[84,126],"adaptation":[85],"framework":[86],"using":[87],"joint":[88,143,170,176],"training":[89],"CNN":[93,114,122,159],"with":[94,125,167,174],"auxiliary":[95,168],"features":[96,100],"i-vector":[97],"fMLLR":[99],"is":[101,123,132,148],"These":[103],"modifications":[104],"give":[105],"substantial":[106],"word":[107],"error":[108],"rate":[109],"reductions":[110],"over":[111],"standard":[113],"used":[115],"as":[116],"baseline.":[117],"Finally":[118],"combined":[124],"LSTM-RNN":[127,175],"acoustic":[128,144],"model":[129,145],"it":[131],"shown":[133],"that":[134],"state-level":[135],"weighted":[136],"log":[137],"likelihood":[138],"score":[139],"combination":[140],"a":[142,161],"decoding":[146],"scheme":[147],"effective.":[150],"On":[151],"task,":[155],"achieves":[160],"WER":[162],"8.81%,":[164],"further":[165],"7.99%":[166],"training,":[171],"7.09%":[173],"decoding.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}