{"id":"https://openalex.org/W2767353373","doi":"https://doi.org/10.1109/icassp.2018.8462456","title":"Robust Speech Recognition Using Generative Adversarial Networks","display_name":"Robust Speech Recognition Using Generative Adversarial Networks","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2767353373","doi":"https://doi.org/10.1109/icassp.2018.8462456","mag":"2767353373"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462456","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.01567","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047764126","display_name":"Anuroop Sriram","orcid":"https://orcid.org/0000-0001-6295-7535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anuroop Sriram","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065707162","display_name":"Heewoo Jun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heewoo Jun","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090158590","display_name":"Sanjeev Satheesh","orcid":"https://orcid.org/0009-0008-5139-1036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanjeev Satheesh","raw_affiliation_strings":["Baidu Research, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research, Sunnyvale, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5639","last_page":"5643"},"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":0.9990000128746033,"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":0.9988999962806702,"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":0.7738136649131775},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7466978430747986},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6964645981788635},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5830081701278687},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5812153220176697},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5121769905090332},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5105191469192505},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4833795428276062},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4777780771255493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46913665533065796},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.328946590423584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738136649131775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7466978430747986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6964645981788635},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5830081701278687},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5812153220176697},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5121769905090332},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5105191469192505},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4833795428276062},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4777780771255493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46913665533065796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.328946590423584},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462456","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"},{"id":"pmh:oai:arXiv.org:1711.01567","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.01567","pdf_url":"https://arxiv.org/pdf/1711.01567","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":"","raw_type":null},{"id":"mag:2767353373","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1711.01567.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1711.01567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1711.01567","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.01567","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.01567","pdf_url":"https://arxiv.org/pdf/1711.01567","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":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2767353373.pdf","grobid_xml":"https://content.openalex.org/works/W2767353373.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522199561","https://openalex.org/W1983812858","https://openalex.org/W2138621090","https://openalex.org/W2164502538","https://openalex.org/W2168961642","https://openalex.org/W2193413348","https://openalex.org/W2404799143","https://openalex.org/W2510867321","https://openalex.org/W2533523411","https://openalex.org/W2600556233","https://openalex.org/W2622203030","https://openalex.org/W2696967604","https://openalex.org/W2739748921","https://openalex.org/W2949117887","https://openalex.org/W2951660826","https://openalex.org/W2962899390","https://openalex.org/W2963827914","https://openalex.org/W6637618735","https://openalex.org/W6638667902","https://openalex.org/W6681096077","https://openalex.org/W6687566353","https://openalex.org/W6732862412","https://openalex.org/W6735488979","https://openalex.org/W6741832134"],"related_works":["https://openalex.org/W2961574602","https://openalex.org/W2924508610","https://openalex.org/W2605488490","https://openalex.org/W2962974744","https://openalex.org/W2593768305","https://openalex.org/W2945178666","https://openalex.org/W3118371074","https://openalex.org/W2963874667","https://openalex.org/W3003416192","https://openalex.org/W3212125355","https://openalex.org/W2961308210","https://openalex.org/W3198932466","https://openalex.org/W2625357353","https://openalex.org/W3089487147","https://openalex.org/W3161549763","https://openalex.org/W2786277362","https://openalex.org/W2990019157","https://openalex.org/W2792311129","https://openalex.org/W2767382337","https://openalex.org/W3042251380"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,66],"general,":[4],"scalable,":[5],"end-to-end":[6],"framework":[7,51],"that":[8,42],"uses":[9],"the":[10,24,37,49,71],"generative":[11],"adversarial":[12],"network":[13],"(GAN)":[14],"objective":[15],"to":[16,32,36],"enable":[17],"robust":[18],"speech":[19,77],"recognition.":[20],"Encoders":[21],"trained":[22],"with":[23],"proposed":[25],"approach":[26,73],"enjoy":[27],"improved":[28],"invariance":[29],"by":[30],"learning":[31],"map":[33],"noisy":[34],"audio":[35],"same":[38],"embedding":[39],"space":[40],"as":[41],"of":[43,79],"clean":[44],"audio.":[45],"Unlike":[46],"previous":[47],"methods,":[48],"new":[50,72],"does":[52],"not":[53],"rely":[54],"on":[55],"domain":[56],"expertise":[57],"or":[58,86],"strong":[59],"assumptions,":[60],"and":[61],"directly":[62],"encourages":[63],"robustness":[64],"in":[65],"data-driven":[67],"way.":[68],"We":[69],"show":[70],"improves":[74],"simulated":[75],"far-field":[76],"recognition":[78],"vanilla":[80],"sequence-to-sequence":[81],"models":[82],"without":[83],"specialized":[84],"front-ends":[85],"preprocessing.":[87]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}