{"id":"https://openalex.org/W4211231901","doi":"https://doi.org/10.1109/cis54983.2021.00032","title":"Adversarial Training with Gated Convolutional Neural Networks for Robust Speech Recognition","display_name":"Adversarial Training with Gated Convolutional Neural Networks for Robust Speech Recognition","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4211231901","doi":"https://doi.org/10.1109/cis54983.2021.00032"},"language":"en","primary_location":{"id":"doi:10.1109/cis54983.2021.00032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cis54983.2021.00032","pdf_url":null,"source":{"id":"https://openalex.org/S4363608286","display_name":"2021 17th International Conference on Computational Intelligence and Security (CIS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Computational Intelligence and Security (CIS)","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/A5085553416","display_name":"Xudong Lv","orcid":"https://orcid.org/0000-0002-7850-6883"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xudong Lv","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Hefei,China,230601","PKU Shenzhen Institute"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"PKU Shenzhen Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102897927","display_name":"Si-Bao Chen","orcid":"https://orcid.org/0000-0003-1481-0162"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si-Bao Chen","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Hefei,China,230601"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Hefei,China,230601","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100617364","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-5854-5287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["PKU Shenzhen Institute"],"affiliations":[{"raw_affiliation_string":"PKU Shenzhen Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085553416"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.172,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44728005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"29","issue":null,"first_page":"113","last_page":"117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987999796867371,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7920347452163696},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7539975047111511},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7293505668640137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6681650876998901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5438253879547119},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5131979584693909},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48689427971839905},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4815833568572998},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4704540967941284},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44335585832595825},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4431094527244568},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4312286078929901},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41183626651763916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33043724298477173},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27183330059051514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920347452163696},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7539975047111511},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7293505668640137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6681650876998901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5438253879547119},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5131979584693909},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48689427971839905},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4815833568572998},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4704540967941284},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44335585832595825},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4431094527244568},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4312286078929901},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41183626651763916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33043724298477173},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27183330059051514},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":1,"locations":[{"id":"doi:10.1109/cis54983.2021.00032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cis54983.2021.00032","pdf_url":null,"source":{"id":"https://openalex.org/S4363608286","display_name":"2021 17th International Conference on Computational Intelligence and Security (CIS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Computational Intelligence and Security (CIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6474056369","display_name":null,"funder_award_id":"61976004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2046932483","https://openalex.org/W2127141656","https://openalex.org/W2296167893","https://openalex.org/W2395579298","https://openalex.org/W2593414223","https://openalex.org/W2936774411","https://openalex.org/W2962684181","https://openalex.org/W2962909949","https://openalex.org/W2962959469","https://openalex.org/W2963242190","https://openalex.org/W2972320711","https://openalex.org/W2981857663","https://openalex.org/W3016010032","https://openalex.org/W3097777922"],"related_works":["https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W2921005841","https://openalex.org/W4380605396","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2584084702","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W3012383599"],"abstract_inverted_index":{"In":[0,43],"natural":[1],"environments,":[2],"the":[3,36,74,84,89,93,110,113,121,124,132,147,155,162],"performance":[4,39,122],"of":[5,50,88,112,123],"automatic":[6],"speech":[7,60],"recognition":[8],"systems":[9],"is":[10,21],"often":[11],"affected":[12],"by":[13,152],"environmental":[14],"noise.":[15],"The":[16],"noise":[17,33,134],"data":[18,135,158],"augmentation":[19,136],"method":[20],"commonly":[22],"used":[23],"to":[24,72,77],"boost":[25],"acoustic":[26,37,75,90,114,125],"models\u2019":[27],"robustness;":[28],"however,":[29],"audios":[30],"with":[31,53,104,131,141],"background":[32],"may":[34],"degrade":[35],"model's":[38],"in":[40,116,127],"clean":[41,156],"audios.":[42],"this":[44],"paper,":[45],"we":[46,82],"propose":[47],"an":[48],"approach":[49],"adversarial":[51,65,102,139],"training":[52,103,137,140],"gated":[54,68,105,142],"convolutional":[55,69,106,143],"neural":[56,70,107,144],"networks":[57,66,71,108,145],"for":[58],"robust":[59],"recognition.":[61],"We":[62],"use":[63],"generative":[64],"and":[67,119,159],"allow":[73],"model":[76,91,115,126],"learn":[78],"noise-invariant":[79],"information.":[80],"Specifically,":[81],"choose":[83],"first":[85],"several":[86],"layers":[87],"as":[92],"generator":[94],"model.":[95],"Systematic":[96],"experiments":[97],"on":[98,154,161],"aishell-1":[99],"show":[100],"that":[101],"boosts":[109],"robustness":[111],"noisy":[117,163],"environments":[118],"improves":[120],"quiet":[128],"environments.":[129],"Compared":[130],"simple":[133],"method,":[138],"reduces":[146],"average":[148],"relative":[149],"error":[150],"rate":[151],"4.4%":[153],"test":[157,164],"5.6%":[160],"data.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}