{"id":"https://openalex.org/W2408583661","doi":"https://doi.org/10.1109/icassp.2016.7472775","title":"Noise robust speech recognition using recent developments in neural networks for computer vision","display_name":"Noise robust speech recognition using recent developments in neural networks for computer vision","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408583661","doi":"https://doi.org/10.1109/icassp.2016.7472775","mag":"2408583661"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472775","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":"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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112092551","display_name":"Katsunori Ohnishi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsunori Ohnishi","raw_affiliation_strings":["NTT Corporation, Japan","University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012466506","display_name":"Fuming Fang","orcid":"https://orcid.org/0000-0002-9332-3735"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fuming Fang","raw_affiliation_strings":["NTT Corporation, Japan","Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7414,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96147789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5730","last_page":"5734"},"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":0.9993000030517578,"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":0.9965000152587891,"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":0.8270342350006104},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.696547269821167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6740288734436035},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6246131062507629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520144522190094},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5179473757743835},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5098404288291931},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5008785724639893},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4708774983882904},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.467768132686615},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.44668492674827576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42934736609458923},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2997317612171173},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13344699144363403},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06890299916267395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270342350006104},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.696547269821167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6740288734436035},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6246131062507629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520144522190094},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5179473757743835},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5098404288291931},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5008785724639893},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4708774983882904},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.467768132686615},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.44668492674827576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42934736609458923},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2997317612171173},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13344699144363403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06890299916267395},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472775","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1555696814","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1799366690","https://openalex.org/W1981617403","https://openalex.org/W1984541135","https://openalex.org/W1995562189","https://openalex.org/W2015337779","https://openalex.org/W2033310064","https://openalex.org/W2035576074","https://openalex.org/W2062227835","https://openalex.org/W2063224314","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2288645994","https://openalex.org/W2397947827","https://openalex.org/W2400885515","https://openalex.org/W2401396087","https://openalex.org/W2962835968","https://openalex.org/W6637373629","https://openalex.org/W6638444622","https://openalex.org/W6674330103","https://openalex.org/W6674914833","https://openalex.org/W6712816420","https://openalex.org/W6713250295","https://openalex.org/W6713281174"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W4220731478","https://openalex.org/W2542937328","https://openalex.org/W4251141768","https://openalex.org/W2964954556"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"are":[4,78],"superior":[5],"to":[6,37,65,74,114],"fully":[7],"connected":[8],"neural":[9],"networks":[10],"in":[11,21,32,95,140,157],"various":[12],"speech":[13,58],"recognition":[14,59,148],"tasks":[15],"and":[16,52],"the":[17,33,67,76,82,106,120,143,158,161],"advantage":[18],"is":[19,64,97,113,129],"pronounced":[20],"noisy":[22,57],"environments.":[23],"In":[24,80],"recent":[25],"years,":[26],"many":[27],"techniques":[28],"have":[29],"been":[30],"proposed":[31],"computer":[34],"vision":[35],"community":[36],"improve":[38],"CNN's":[39],"classification":[40,51],"performance.":[41,60,141],"This":[42],"paper":[43],"considers":[44],"two":[45,144],"approaches":[46,73,136,145],"recently":[47],"developed":[48],"for":[49,165],"image":[50],"examines":[53],"their":[54],"impacts":[55],"on":[56],"The":[61,110],"first":[62],"approach":[63,112],"increase":[66],"depth":[68],"of":[69,84,105,122,155],"convolution":[70,90,94,108],"layers.":[71],"Different":[72],"deepening":[75],"CNNs":[77],"compared.":[79],"particular,":[81],"usefulness":[83],"learning":[85],"dynamic":[86],"features":[87],"with":[88,100,168],"small":[89],"layers":[91],"that":[92,134],"perform":[93],"time":[96],"shown":[98],"along":[99],"a":[101,123,151,169],"modulation":[102],"frequency":[103],"analysis":[104],"learned":[107],"filters.":[109],"second":[111],"use":[115,121],"trainable":[116],"activation":[117],"functions.":[118],"Specifically,":[119],"Parametric":[124],"Rectified":[125],"Linear":[126],"Unit":[127],"(PReLU)":[128],"investigated.":[130],"Experimental":[131],"results":[132],"show":[133],"both":[135],"yield":[137],"significant":[138],"improvements":[139],"Combining":[142],"further":[146],"reduces":[147],"errors,":[149],"producing":[150],"word":[152],"error":[153],"rate":[154],"11.1%":[156],"Aurora4":[159],"task,":[160],"best":[162],"published":[163],"result":[164],"this":[166],"corpus,":[167],"standard":[170],"one-pass":[171],"bi-gram":[172],"decoding":[173],"set-up.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}