{"id":"https://openalex.org/W3041872649","doi":"https://doi.org/10.1109/isqed48828.2020.9136978","title":"Deep Neural Network Based Speech Recognition Systems Under Noise Perturbations","display_name":"Deep Neural Network Based Speech Recognition Systems Under Noise Perturbations","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3041872649","doi":"https://doi.org/10.1109/isqed48828.2020.9136978","mag":"3041872649"},"language":"en","primary_location":{"id":"doi:10.1109/isqed48828.2020.9136978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed48828.2020.9136978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 21st International Symposium on Quality Electronic Design (ISQED)","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/A5041955234","display_name":"Qiyuan An","orcid":"https://orcid.org/0000-0003-4712-891X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiyuan An","raw_affiliation_strings":["Virginia Tech, 1185 Perry St, Virginia, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, 1185 Perry St, Virginia, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082108426","display_name":"Kangjun Bai","orcid":"https://orcid.org/0000-0003-4437-0006"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kangjun Bai","raw_affiliation_strings":["Virginia Tech, 1185 Perry St, Virginia, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, 1185 Perry St, Virginia, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008512472","display_name":"Moqi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moqi Zhang","raw_affiliation_strings":["Virginia Tech, 1185 Perry St, Virginia, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, 1185 Perry St, Virginia, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018632091","display_name":"Yang Yi","orcid":"https://orcid.org/0000-0002-1354-0204"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Yi","raw_affiliation_strings":["Virginia Tech, 1185 Perry St, Virginia, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, 1185 Perry St, Virginia, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049048133","display_name":"Yifang Liu","orcid":"https://orcid.org/0000-0003-3800-5512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifang Liu","raw_affiliation_strings":["Smule Inc,, 139 Townsend St, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smule Inc,, 139 Townsend St, San Francisco, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1643,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.31222675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"93","issue":null,"first_page":"377","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.7991888523101807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.754733681678772},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7311912775039673},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.6288083791732788},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6286848187446594},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5959395170211792},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5879262685775757},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5838115215301514},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.577597975730896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46901601552963257},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4312882721424103},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42804965376853943},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41152721643447876},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4051280617713928},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15189707279205322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991888523101807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.754733681678772},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7311912775039673},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.6288083791732788},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6286848187446594},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5959395170211792},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5879262685775757},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5838115215301514},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.577597975730896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46901601552963257},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4312882721424103},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42804965376853943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41152721643447876},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4051280617713928},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15189707279205322},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isqed48828.2020.9136978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed48828.2020.9136978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 21st International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1506438021","https://openalex.org/W1524333225","https://openalex.org/W1673923490","https://openalex.org/W1924770834","https://openalex.org/W1945616565","https://openalex.org/W1995562189","https://openalex.org/W2007321142","https://openalex.org/W2064675550","https://openalex.org/W2099733939","https://openalex.org/W2105705305","https://openalex.org/W2115730999","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2213952365","https://openalex.org/W2257979135","https://openalex.org/W2294132199","https://openalex.org/W2394932179","https://openalex.org/W2782403400","https://openalex.org/W2794209590","https://openalex.org/W2946347869","https://openalex.org/W2954387231","https://openalex.org/W2963037989","https://openalex.org/W2963207607","https://openalex.org/W2964153729","https://openalex.org/W2964227577","https://openalex.org/W2964301649","https://openalex.org/W2979610412","https://openalex.org/W3104896896","https://openalex.org/W6630245200","https://openalex.org/W6631362777","https://openalex.org/W6711962127"],"related_works":["https://openalex.org/W2120446725","https://openalex.org/W1494724239","https://openalex.org/W2111680118","https://openalex.org/W4246803324","https://openalex.org/W2159897332","https://openalex.org/W2284565437","https://openalex.org/W1540849649","https://openalex.org/W4367598165","https://openalex.org/W1969920786","https://openalex.org/W303642266"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,35,70,81],"recognition,":[2],"which":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,33,63],"human-computer":[9],"interactions,":[10],"is":[11,76,113],"the":[12,22,58,69,74,79,88,95,107,111,116,122],"cornerstone":[13],"of":[14,60],"communication":[15],"between":[16],"human":[17],"and":[18],"smart":[19],"devices.":[20],"In":[21,53],"past":[23],"few":[24],"years,":[25],"deep":[26],"neural":[27,65,103,132],"networks":[28],"(DNNs)":[29],"have":[30],"been":[31],"deployed":[32],"automatic":[34],"recognition":[36,71],"with":[37],"great":[38],"success.":[39],"However,":[40],"recent":[41],"research":[42],"has":[43],"discovered":[44],"that":[45,87],"DNNs":[46],"are":[47],"not":[48],"robust":[49],"against":[50],"small":[51],"perturbations.":[52],"this":[54],"work,":[55],"we":[56],"investigate":[57],"capability":[59],"noise":[61,75,112],"immunity":[62],"various":[64],"network":[66,104,126,133],"models":[67],"through":[68],"task.":[72],"When":[73],"introduced":[77,114],"into":[78,115],"original":[80],"audio,":[82],"our":[83],"experimental":[84],"results":[85],"demonstrate":[86],"phoneme":[89],"error":[90],"rate":[91],"(PER)":[92],"degrades":[93],"as":[94],"signal-to-noise":[96],"ratio":[97],"(SNR)":[98],"reduces":[99],"across":[100],"all":[101,129],"evaluated":[102],"models.":[105,135],"On":[106],"other":[108,130],"hand,":[109],"when":[110],"Mel-frequency":[117],"cepstral":[118],"coefficient":[119],"(MFCC)":[120],"features,":[121],"multilayer":[123],"perceptron":[124],"(MLP)":[125],"model":[127],"outperforms":[128],"recurrent":[131],"(RNN)":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}