{"id":"https://openalex.org/W2797187289","doi":"https://doi.org/10.1109/taslp.2018.2825432","title":"Adaptive Very Deep Convolutional Residual Network for Noise Robust Speech Recognition","display_name":"Adaptive Very Deep Convolutional Residual Network for Noise Robust Speech Recognition","publication_year":2018,"publication_date":"2018-04-12","ids":{"openalex":"https://openalex.org/W2797187289","doi":"https://doi.org/10.1109/taslp.2018.2825432","mag":"2797187289"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2825432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2825432","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101667381","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0002-4723-0044"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4723-0044","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079582557","display_name":"Hu Hu","orcid":"https://orcid.org/0000-0003-2101-8317"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Hu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722576","display_name":"Ying Zhou","orcid":"https://orcid.org/0000-0002-4082-7497"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhou","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4082-7497","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101864742","display_name":"Wen Ding","orcid":"https://orcid.org/0000-0002-4308-4182"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Ding","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4308-4182","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":9.0798,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.98191686,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"26","issue":"8","first_page":"1393","last_page":"1405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.8197219967842102},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6980718374252319},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6866594552993774},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6671521067619324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6404698491096497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5148738622665405},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5142226219177246},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.505704402923584},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4762290120124817},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4361165761947632},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40595805644989014},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1579797863960266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197219967842102},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6980718374252319},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6866594552993774},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6671521067619324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6404698491096497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5148738622665405},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5142226219177246},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.505704402923584},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4762290120124817},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4361165761947632},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40595805644989014},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1579797863960266},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2825432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2825432","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1513820424","https://openalex.org/W1513984940","https://openalex.org/W1524333225","https://openalex.org/W1567690964","https://openalex.org/W1571447047","https://openalex.org/W1592672653","https://openalex.org/W1600744878","https://openalex.org/W1836465849","https://openalex.org/W1943324956","https://openalex.org/W1976637928","https://openalex.org/W1992475611","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2024490156","https://openalex.org/W2033310064","https://openalex.org/W2039716246","https://openalex.org/W2048526313","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2080921589","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2094147890","https://openalex.org/W2112739286","https://openalex.org/W2115086266","https://openalex.org/W2119203697","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2293634267","https://openalex.org/W2302255633","https://openalex.org/W2394882406","https://openalex.org/W2394932179","https://openalex.org/W2395655916","https://openalex.org/W2397042577","https://openalex.org/W2397947827","https://openalex.org/W2400339399","https://openalex.org/W2402201734","https://openalex.org/W2404404182","https://openalex.org/W2406264770","https://openalex.org/W2407023693","https://openalex.org/W2491899193","https://openalex.org/W2508162385","https://openalex.org/W2514021858","https://openalex.org/W2515753980","https://openalex.org/W2515863432","https://openalex.org/W2519224033","https://openalex.org/W2530876040","https://openalex.org/W2587717635","https://openalex.org/W2604132379","https://openalex.org/W2616139854","https://openalex.org/W2916986993","https://openalex.org/W2963217176","https://openalex.org/W2963266252","https://openalex.org/W3125118953","https://openalex.org/W6603403951","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6639288305","https://openalex.org/W6677416784","https://openalex.org/W6686045668","https://openalex.org/W6696934422","https://openalex.org/W6711962127","https://openalex.org/W6712213709","https://openalex.org/W6712816420","https://openalex.org/W6713149780","https://openalex.org/W6714171909"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2037265366","https://openalex.org/W2022849831","https://openalex.org/W2391832549","https://openalex.org/W2286653370","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W1799937301","https://openalex.org/W4297807321"],"abstract_inverted_index":{"Although":[0],"great":[1],"progress":[2],"has":[3,21],"been":[4],"made":[5],"in":[6,15,126,143,159],"automatic":[7],"speech":[8],"recognition,":[9],"significant":[10,202],"performance":[11,158],"degradation":[12],"still":[13],"exists":[14],"noisy":[16,161,209,218],"environments.":[17],"Our":[18],"previous":[19,70],"work":[20,37],"demonstrated":[22],"the":[23,50,74,77,92,124,127,155,160,194,224,231,240,260],"superior":[24],"noise":[25,178,190],"robustness":[26,68],"of":[27,134],"very":[28,51,252],"deep":[29,52],"convolutional":[30,53],"neural":[31],"networks":[32],"(VDCNN).":[33],"Based":[34],"on":[35,38,98,169,233,255,268],"our":[36],"VDCNNs,":[39],"this":[40,234],"paper":[41,96],"proposes":[42],"a":[43,110,131,147,270],"more":[44,67,228],"advanced":[45],"model":[46,59,82,235],"referred":[47],"to":[48,72,122,138,153,259],"as":[49],"residual":[54,64],"network":[55],"(VDCRN).":[56],"This":[57,95],"new":[58,93,165,225,271],"incorporates":[60],"batch":[61],"normalization":[62],"and":[63,79,84,89,103,179,185,191,193,216,230,251],"learning,":[65],"showing":[66],"than":[69],"VDCNNs.Then,":[71],"alleviate":[73],"mismatch":[75],"between":[76],"training":[78,86,101,106],"testing":[80],"conditions,":[81,210],"adaptation":[83,232],"adaptive":[85,105],"are":[87,119,167],"developed":[88],"compared":[90,258],"for":[91],"VDCRN.":[94],"focuses":[97],"factor":[99],"aware":[100],"(FAT)":[102],"cluster":[104],"(CAT).":[107],"For":[108,115],"FAT,":[109],"unified":[111],"framework":[112],"is":[113,136,151,227,275],"explored.":[114],"CAT,":[116],"two":[117],"schemes":[118],"first":[120],"explored":[121],"construct":[123],"bases":[125],"canonical":[128],"model;":[129],"furthermore,":[130],"factorized":[132],"version":[133],"CAT":[135],"designed":[137],"address":[139],"multiple":[140],"nonspeech":[141],"variabilities":[142],"one":[144],"model.":[145],"Finally,":[146],"complete":[148],"multipass":[149],"system":[150,157],"proposed":[152,164,246],"achieve":[154],"best":[156,247],"scenarios.":[162],"The":[163,220,245],"approaches":[166],"evaluated":[168],"three":[170],"different":[171,208],"tasks:":[172],"Aurora4":[173,269],"(simulated":[174],"data":[175,187,200],"with":[176,188,201],"additive":[177,189],"channel":[180],"distortion),":[181],"CHiME4":[182],"(both":[183],"simulated":[184,215],"real":[186,217],"reverberation),":[192],"AMI":[195],"meeting":[196],"transcription":[197],"task":[198],"(real":[199],"reverberation).The":[203],"evaluation":[204],"not":[205],"only":[206,278],"includes":[207],"but":[211],"also":[212],"covers":[213],"both":[214],"data.":[219],"experiments":[221],"show":[222],"that":[223],"VDCRN":[226],"robust,":[229],"can":[236],"further":[237],"significantly":[238],"reduce":[239],"word":[241],"error":[242],"rate":[243],"(WER).":[244],"architecture":[248],"obtains":[249],"consistent":[250],"large":[253],"improvements":[254],"all":[256],"tasks":[257],"baseline":[261],"VDCNN":[262],"or":[263],"long":[264],"short-term":[265],"memory.":[266],"Particularly,":[267],"milestone":[272],"5.67%":[273],"WER":[274],"achieved":[276],"by":[277],"improving":[279],"acoustic":[280],"modeling.":[281]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":8}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}