{"id":"https://openalex.org/W2944394478","doi":"https://doi.org/10.1109/iscslp.2018.8706651","title":"Data Augmentation using Conditional Generative Adversarial Networks for Robust Speech Recognition","display_name":"Data Augmentation using Conditional Generative Adversarial Networks for Robust Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944394478","doi":"https://doi.org/10.1109/iscslp.2018.8706651","mag":"2944394478"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5034260681","display_name":"Peiyao Sheng","orcid":null},"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":"Peiyao Sheng","raw_affiliation_strings":["SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044586758","display_name":"Zhuolin Yang","orcid":"https://orcid.org/0000-0002-6017-8818"},"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":"Zhuolin Yang","raw_affiliation_strings":["SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Research Center 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":["SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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":["SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","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":["SpeechLab, Research Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Research Center 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":null,"apc_paid":null,"fwci":0.8311,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.75319426,"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":"121","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.7451637387275696},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.704035758972168},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5686004161834717},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5487982034683228},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5351181030273438},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5188809037208557},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.48084625601768494},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47018492221832275},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.45476892590522766},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4353301525115967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41069236397743225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3892592489719391},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24822956323623657},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1031976044178009},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05990570783615112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451637387275696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.704035758972168},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5686004161834717},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5487982034683228},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5351181030273438},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5188809037208557},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.48084625601768494},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47018492221832275},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.45476892590522766},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4353301525115967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41069236397743225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3892592489719391},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24822956323623657},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1031976044178009},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05990570783615112},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"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/iscslp.2018.8706651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1976637928","https://openalex.org/W2099471712","https://openalex.org/W2119203697","https://openalex.org/W2125389028","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2394932179","https://openalex.org/W2515753980","https://openalex.org/W2548275288","https://openalex.org/W2608338293","https://openalex.org/W2617258110","https://openalex.org/W2666408839","https://openalex.org/W2696967604","https://openalex.org/W2746457594","https://openalex.org/W2749371885","https://openalex.org/W2767064007","https://openalex.org/W2787069756","https://openalex.org/W2797187289","https://openalex.org/W2891138528","https://openalex.org/W2891756742","https://openalex.org/W2950776302","https://openalex.org/W2962896155","https://openalex.org/W2963073614","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963364041","https://openalex.org/W2963373786","https://openalex.org/W2963709863","https://openalex.org/W2963971656","https://openalex.org/W2964201867","https://openalex.org/W4320013936","https://openalex.org/W6631362777","https://openalex.org/W6678815747","https://openalex.org/W6711962127","https://openalex.org/W6718379498","https://openalex.org/W6729482032","https://openalex.org/W6729966448","https://openalex.org/W6731344955","https://openalex.org/W6732249622","https://openalex.org/W6735429107","https://openalex.org/W6737196085","https://openalex.org/W6738243166","https://openalex.org/W6739699547","https://openalex.org/W6739992741","https://openalex.org/W6741347854","https://openalex.org/W6742802039","https://openalex.org/W6744040789","https://openalex.org/W6745822563","https://openalex.org/W6747969919","https://openalex.org/W6754402303","https://openalex.org/W6754558276","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W3178813832","https://openalex.org/W4377980832","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4226298148","https://openalex.org/W2972144487","https://openalex.org/W2845413374","https://openalex.org/W4327672426"],"abstract_inverted_index":{"For":[0],"noise":[1,26,125],"robust":[2],"speech":[3,43,61,77,84,87],"recognition,":[4],"data":[5,22,41,56,103,113],"mismatch":[6],"between":[7],"training":[8],"and":[9,79,105,121,133,150],"test":[10],"is":[11,116],"a":[12,151],"significant":[13],"challenge.":[14],"To":[15],"reduce":[16],"this":[17,46],"mismatch,":[18],"traditional":[19],"approach":[20,115],"of":[21],"augmentation":[23,57,114],"usually":[24],"adds":[25],"to":[27,39,58,154],"original":[28,81],"waveform":[29],"directly.":[30,109],"A":[31],"recent":[32],"work":[33],"utilizes":[34],"generative":[35,51],"adversarial":[36,52],"network":[37,53],"(GAN)":[38],"generate":[40],"for":[42,55,75,85],"recognition.":[44],"In":[45],"work,":[47],"we":[48],"explore":[49],"conditional":[50],"(cGAN)":[54],"further":[59],"improve":[60],"recognition":[62],"in":[63],"noisy":[64,148],"environments.":[65],"Two":[66],"different":[67],"conditions":[68,101],"are":[69],"explored,":[70],"including":[71],"the":[72,80,99,139],"acoustic":[73,164],"state":[74],"each":[76,86],"frame":[78],"paired":[82],"clean":[83],"frame.":[88],"Different":[89],"from":[90],"using":[91],"basic":[92],"GAN,":[93],"these":[94],"newly":[95],"designed":[96],"cGANs":[97],"incorporate":[98],"specific":[100],"into":[102],"generation":[104],"provide":[106],"true":[107],"labels":[108],"The":[110],"proposed":[111],"cGAN-based":[112,140],"evaluated":[117],"on":[118],"both":[119],"Aurora4":[120],"AMI-SDM,":[122],"which":[123],"have":[124],"types":[126],"such":[127],"as":[128],"additive":[129],"noise,":[130],"channel":[131],"distortion":[132],"reverberation.":[134],"Experimental":[135],"results":[136],"show":[137],"that":[138],"method":[141],"consistently":[142],"outperforms":[143],"GAN-based":[144],"one":[145],"under":[146],"all":[147],"conditions,":[149],"relative":[152],"6%":[153],"10%":[155],"WER":[156],"reduction":[157],"can":[158],"be":[159],"obtained":[160],"upon":[161],"an":[162],"advanced":[163],"model.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}