{"id":"https://openalex.org/W2962959469","doi":"https://doi.org/10.1109/icassp.2018.8462093","title":"Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training","display_name":"Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962959469","doi":"https://doi.org/10.1109/icassp.2018.8462093","mag":"2962959469"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100395562","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0003-1529-1552"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068044387","display_name":"Shuai Nie","orcid":"https://orcid.org/0000-0002-8078-6829"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Nie","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090919681","display_name":"Yaping Zhang","orcid":"https://orcid.org/0000-0001-6892-905X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaping Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["National Laboratory of Patten Recognition, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Patten Recognition, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108575841","display_name":"Shan Liang","orcid":"https://orcid.org/0000-0002-9734-9166"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Liang","raw_affiliation_strings":["National Laboratory of Patten Recognition, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Patten Recognition, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039635290","display_name":"Wenju Liu","orcid":"https://orcid.org/0000-0001-9088-8282"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenju Liu","raw_affiliation_strings":["National Laboratory of Patten Recognition, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Patten Recognition, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100395562"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.1469,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88901412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5034","last_page":"5038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9965999722480774,"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":0.9947999715805054,"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":0.8035275936126709},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7747327089309692},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7520173788070679},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6847937107086182},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5141787528991699},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4470774233341217},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.44177860021591187},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4323011636734009},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4294307827949524},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42691951990127563},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.42387694120407104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4147687554359436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40196770429611206},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.38185665011405945},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3546445369720459},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13408613204956055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8035275936126709},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7747327089309692},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7520173788070679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6847937107086182},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5141787528991699},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4470774233341217},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.44177860021591187},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4323011636734009},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4294307827949524},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42691951990127563},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.42387694120407104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4147687554359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40196770429611206},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.38185665011405945},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3546445369720459},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13408613204956055},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1598508708","https://openalex.org/W1665214252","https://openalex.org/W1901129140","https://openalex.org/W1995536493","https://openalex.org/W2008971146","https://openalex.org/W2010362084","https://openalex.org/W2025768430","https://openalex.org/W2042141988","https://openalex.org/W2062164080","https://openalex.org/W2095705004","https://openalex.org/W2113556376","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2412510955","https://openalex.org/W2559260703","https://openalex.org/W2593414223","https://openalex.org/W2748379347","https://openalex.org/W2749371885","https://openalex.org/W2962896155","https://openalex.org/W2963073614","https://openalex.org/W2963250052","https://openalex.org/W2963341071","https://openalex.org/W2963684088","https://openalex.org/W2964218010","https://openalex.org/W4295274059","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2401089611","https://openalex.org/W3081187864","https://openalex.org/W151018310","https://openalex.org/W4380605396","https://openalex.org/W2584084702","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W3012383599","https://openalex.org/W4385611764","https://openalex.org/W172230311"],"abstract_inverted_index":{"In":[0,64,77],"realistic":[1],"environments,":[2],"speech":[3,19,35,66,71,162],"is":[4,30,110,117],"usually":[5],"interfered":[6],"by":[7,127],"various":[8],"noise":[9,89,176],"and":[10,49,73,104,142,151,159,180,190,195],"reverberation,":[11],"which":[12],"dramatically":[13],"degrades":[14],"the":[15,27,39,113,128,138,154,170,175,182,193],"performance":[16],"of":[17,41,62,91,99,130,148,156,178,188],"automatic":[18],"recognition":[20],"(ASR)":[21],"systems.":[22],"To":[23],"alleviate":[24],"this":[25,60,78],"issue,":[26],"commonest":[28],"way":[29],"to":[31,75,86,119,135],"use":[32],"a":[33,95,131],"well-designed":[34],"enhancement":[36,67],"approach":[37],"as":[38],"front-end":[40],"ASR.":[42],"However,":[43],"more":[44,47],"complex":[45],"pipelines,":[46],"computations":[48],"even":[50],"higher":[51],"hardware":[52],"costs":[53],"(microphone":[54],"array)":[55],"are":[56],"additionally":[57],"consumed":[58],"for":[59,161],"kind":[61],"methods.":[63],"addition,":[65],"would":[68],"result":[69],"in":[70,112],"distortions":[72],"mismatches":[74],"training.":[76],"paper,":[79],"we":[80],"propose":[81],"an":[82],"adversarial":[83,101],"training":[84,114],"method":[85,172],"directly":[87],"boost":[88],"robustness":[90,177],"acoustic":[92,107],"model.":[93],"Specifically,":[94],"jointly":[96],"compositional":[97],"scheme":[98],"generative":[100],"net":[102],"(GAN)":[103],"neural":[105],"network-based":[106],"model":[108],"(AM)":[109],"used":[111,118],"phase.":[115],"GAN":[116,158],"generate":[120],"clean":[121,140],"feature":[122],"representations":[123],"from":[124],"noisy":[125],"features":[126],"guidance":[129],"discriminator":[132,150],"that":[133,169],"tries":[134],"distinguish":[136],"between":[137],"true":[139],"signals":[141],"generated":[143],"signals.":[144],"The":[145],"joint":[146],"optimization":[147],"generator,":[149],"AM":[152,160,179],"concentrates":[153],"strengths":[155],"both":[157],"recognition.":[163],"Systematic":[164],"experiments":[165],"on":[166,192],"CHiME-4":[167],"show":[168],"proposed":[171],"significantly":[173],"improves":[174],"achieves":[181],"average":[183],"relative":[184],"error":[185],"rate":[186],"reduction":[187],"23.38%":[189],"11.54%":[191],"development":[194],"test":[196],"set,":[197],"respectively.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}