{"id":"https://openalex.org/W2008971146","doi":"https://doi.org/10.1109/asru.2013.6707743","title":"Improving robustness of deep neural networks via spectral masking for automatic speech recognition","display_name":"Improving robustness of deep neural networks via spectral masking for automatic speech recognition","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2008971146","doi":"https://doi.org/10.1109/asru.2013.6707743","mag":"2008971146"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5100772205","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-9025-8985"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":3.5223,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94379085,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robustness","display_name":"Robustness (evolution)","score":0.7870181202888489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7856315970420837},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793367505073547},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5691125988960266},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5452197194099426},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5194527506828308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.493857204914093},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43432796001434326},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4227578341960907},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2861209511756897}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7870181202888489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7856315970420837},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793367505073547},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5691125988960266},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5452197194099426},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5194527506828308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.493857204914093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43432796001434326},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4227578341960907},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2861209511756897},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2013.6707743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/78187","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/78187","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W160800111","https://openalex.org/W178522393","https://openalex.org/W1524333225","https://openalex.org/W1966849888","https://openalex.org/W1979005715","https://openalex.org/W1988843652","https://openalex.org/W2027701650","https://openalex.org/W2030237556","https://openalex.org/W2035576074","https://openalex.org/W2062164080","https://openalex.org/W2066850331","https://openalex.org/W2087126002","https://openalex.org/W2113343909","https://openalex.org/W2115730999","https://openalex.org/W2118497033","https://openalex.org/W2132037657","https://openalex.org/W2141411743","https://openalex.org/W2146083413","https://openalex.org/W2150866759","https://openalex.org/W2151484683","https://openalex.org/W2172097686","https://openalex.org/W2213952365","https://openalex.org/W2290318471","https://openalex.org/W2408592723","https://openalex.org/W2561557072","https://openalex.org/W4233392025","https://openalex.org/W6631362777","https://openalex.org/W6641958222","https://openalex.org/W6659187427","https://openalex.org/W6713796627"],"related_works":["https://openalex.org/W2770665941","https://openalex.org/W2309273277","https://openalex.org/W3096184950","https://openalex.org/W4379116102","https://openalex.org/W2061937230","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W4231424160"],"abstract_inverted_index":{"The":[0,66,128],"performance":[1,107],"of":[2,21,108,131,140],"human":[3],"listeners":[4],"degrades":[5],"rather":[6],"slowly":[7],"compared":[8],"to":[9,18,31,54,73,79,99,104,124],"machines":[10],"in":[11],"noisy":[12],"environments.":[13],"This":[14],"has":[15,69],"been":[16,70],"attributed":[17],"the":[19,28,43,47,75,80,106,109,115,125,132],"ability":[20],"performing":[22],"auditory":[23],"scene":[24],"analysis":[25],"which":[26],"separates":[27],"speech":[29,56,89],"prior":[30],"recognition.":[32],"In":[33],"this":[34],"work,":[35],"we":[36],"investigate":[37],"two":[38,133],"mask":[39],"estimation":[40],"approaches,":[41],"namely":[42],"state":[44],"dependent":[45],"and":[46,85,102,144],"deep":[48],"neural":[49],"network":[50],"(DNN)":[51],"based":[52,83],"estimations,":[53],"separate":[55],"from":[57],"noises":[58],"for":[59,88],"improving":[60],"DNN":[61],"acoustic":[62],"models'":[63],"noise":[64],"robustness.":[65],"second":[67],"approach":[68],"experimentally":[71],"shown":[72],"outperform":[74],"first":[76],"one.":[77],"Due":[78],"stereo":[81],"data":[82],"training":[84],"ill-defined":[86],"masks":[87],"with":[90],"channel":[91],"distortions,":[92],"both":[93],"methods":[94],"do":[95],"not":[96],"generalize":[97],"well":[98],"unseen":[100],"conditions":[101],"fail":[103],"beat":[105],"multi-style":[110],"trained":[111,117],"baseline":[112,126],"system.":[113],"However,":[114],"model":[116],"on":[118,142,146],"masked":[119],"features":[120],"demonstrates":[121],"strong":[122],"complementariness":[123],"model.":[127],"simple":[129],"average":[130],"system's":[134],"posteriors":[135],"yields":[136],"word":[137],"error":[138],"rates":[139],"4.4%":[141],"Aurora2":[143],"12.3%":[145],"Aurora4.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}