{"id":"https://openalex.org/W2795050058","doi":"https://doi.org/10.21437/interspeech.2018-1780","title":"Investigating Generative Adversarial Networks Based Speech Dereverberation for Robust Speech Recognition","display_name":"Investigating Generative Adversarial Networks Based Speech Dereverberation for Robust Speech Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2795050058","doi":"https://doi.org/10.21437/interspeech.2018-1780","mag":"2795050058"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1780","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.10132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100628775","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-0797-4655"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke Wang","raw_affiliation_strings":["Xiaomi, Beijing, China","Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102880200","display_name":"Sining Sun","orcid":"https://orcid.org/0000-0002-2642-5096"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sining Sun","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081342676","display_name":"Xiang Fei","orcid":"https://orcid.org/0000-0002-0877-7047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Xiang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100628775"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":4.978,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96116948,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1581","last_page":"1585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9983999729156494,"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":0.9980999827384949,"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/discriminator","display_name":"Discriminator","score":0.9246324300765991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8392370343208313},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7777586579322815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7301948070526123},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.662299633026123},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5826146602630615},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5338807106018066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3245204985141754},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1136818528175354},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08117929100990295}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9246324300765991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392370343208313},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7777586579322815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7301948070526123},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.662299633026123},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5826146602630615},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5338807106018066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3245204985141754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1136818528175354},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08117929100990295},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1780","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.10132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10132","pdf_url":"https://arxiv.org/pdf/1803.10132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.10132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10132","pdf_url":"https://arxiv.org/pdf/1803.10132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1797288984","https://openalex.org/W1973207880","https://openalex.org/W1982728343","https://openalex.org/W2006129368","https://openalex.org/W2042071805","https://openalex.org/W2048981179","https://openalex.org/W2078528584","https://openalex.org/W2107992675","https://openalex.org/W2110322414","https://openalex.org/W2118446434","https://openalex.org/W2125389028","https://openalex.org/W2153418894","https://openalex.org/W2242685705","https://openalex.org/W2243943790","https://openalex.org/W2293634267","https://openalex.org/W2399557756","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2542605056","https://openalex.org/W2588610957","https://openalex.org/W2593414223","https://openalex.org/W2609317876","https://openalex.org/W2687223163","https://openalex.org/W2696967604","https://openalex.org/W2746457594","https://openalex.org/W2747732471","https://openalex.org/W2749588430","https://openalex.org/W2916979304","https://openalex.org/W2963073614","https://openalex.org/W2963300719","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2964121744","https://openalex.org/W2964286182","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966","https://openalex.org/W2969399009"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,43,61,72,106,111,120,129,132,135,157,173],"use":[3,62],"of":[4,32,45,63,74,122],"generative":[5],"adversarial":[6],"networks":[7,77],"(GANs)":[8],"in":[9,39,60,67,80,97,105,152],"speech":[10,14,22,40],"dereverberation":[11,41,65,76,163,176],"for":[12,21,119],"robust":[13],"recognition.":[15],"GANs":[16,47],"have":[17,48],"been":[18,50],"recently":[19],"studied":[20],"enhancement":[23],"to":[24,35,127,148,172],"remove":[25],"additive":[26],"noises,":[27],"but":[28],"there":[29],"still":[30],"lacks":[31],"a":[33,87,146,181],"work":[34],"examine":[36],"their":[37],"ability":[38],"and":[42,82,95,131],"advantages":[44],"using":[46,134,142],"not":[49],"fully":[51],"established.":[52],"In":[53,159],"this":[54],"paper,":[55],"we":[56,70,116],"provide":[57],"deep":[58,107],"investigations":[59],"GAN-based":[64,162],"front-end":[66,164],"ASR.":[68],"First,":[69],"study":[71],"effectiveness":[73],"different":[75],"(the":[78],"generator":[79,130],"GAN)":[81],"find":[83,117],"that":[84],"LSTM":[85],"leads":[86],"significant":[88],"improvement":[89],"as":[90,113,145,150,170],"compared":[91,171],"with":[92],"feed-forward":[93],"DNN":[94,175],"CNN":[96],"our":[98,161],"dataset.":[99],"Second,":[100],"further":[101],"adding":[102],"residual":[103],"connections":[104],"LSTMs":[108],"can":[109],"boost":[110],"performance":[112],"well.":[114],"Finally,":[115],"that,":[118],"success":[121],"GAN,":[123],"it":[124],"is":[125],"important":[126],"update":[128],"discriminator":[133],"same":[136],"mini-batch":[137],"data":[138],"during":[139],"training.":[140],"Moreover,":[141],"reverberant":[143],"spectrogram":[144],"condition":[147],"discriminator,":[149],"suggested":[151],"previous":[153],"studies,":[154],"may":[155],"degrade":[156],"performance.":[158],"summary,":[160],"achieves":[165],"14%-19%":[166],"relative":[167],"CER":[168],"reduction":[169],"baseline":[174],"network":[177],"when":[178],"tested":[179],"on":[180],"strong":[182],"multi-condition":[183],"training":[184],"acoustic":[185],"model.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}