{"id":"https://openalex.org/W4400527025","doi":"https://doi.org/10.1109/gem61861.2024.10585411","title":"Revisiting Generative Adversarial Network for Downstream Task of Speech Recognition","display_name":"Revisiting Generative Adversarial Network for Downstream Task of Speech Recognition","publication_year":2024,"publication_date":"2024-06-05","ids":{"openalex":"https://openalex.org/W4400527025","doi":"https://doi.org/10.1109/gem61861.2024.10585411"},"language":"en","primary_location":{"id":"doi:10.1109/gem61861.2024.10585411","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gem61861.2024.10585411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Gaming, Entertainment, and Media Conference (GEM)","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/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sheng Li","raw_affiliation_strings":["NICT,Advanced Speech Technology Laboratory,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"NICT,Advanced Speech Technology Laboratory,Kyoto,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910830","display_name":"Bei Liu","orcid":"https://orcid.org/0000-0002-6208-003X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Liu","raw_affiliation_strings":["Multimedia Search and Mining Group, Microsoft Research Asia,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Multimedia Search and Mining Group, Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Multimedia Search and Mining Group, Microsoft Research Asia,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Multimedia Search and Mining Group, Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053726259"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11174171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9388999938964844,"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":0.9388999938964844,"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/adversarial-system","display_name":"Adversarial system","score":0.7463885545730591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7067131400108337},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.6808153390884399},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6567704677581787},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6154698133468628},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.5237467288970947},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44842085242271423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41201624274253845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4035283029079437},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.13082915544509888},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10694432258605957}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7463885545730591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067131400108337},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.6808153390884399},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6567704677581787},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6154698133468628},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.5237467288970947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44842085242271423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41201624274253845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4035283029079437},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.13082915544509888},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10694432258605957},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gem61861.2024.10585411","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gem61861.2024.10585411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Gaming, Entertainment, and Media Conference (GEM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1935589317","https://openalex.org/W1989314204","https://openalex.org/W2042071805","https://openalex.org/W2044893557","https://openalex.org/W2078528584","https://openalex.org/W2141411743","https://openalex.org/W2147166770","https://openalex.org/W2289480995","https://openalex.org/W2795050058","https://openalex.org/W2886938596","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2888032422","https://openalex.org/W3156763702","https://openalex.org/W4385421777","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"The":[0],"generative":[1],"adversarial":[2],"network":[3],"(GAN)-based":[4],"method":[5,107],"was":[6],"used":[7],"effectively":[8],"to":[9,38,112],"address":[10],"environmental":[11],"mismatches":[12],"and":[13,19,108],"speech":[14,27,33,74],"distortion":[15],"caused":[16],"by":[17],"noise":[18],"reverberation,":[20],"substan-tially":[21],"improving":[22],"the":[23,31,39,53,70,78,95,104,110],"accuracy":[24],"of":[25,55],"automatic":[26],"recognition":[28,34],"(ASR)":[29],"in":[30,81],"distant":[32],"task.":[35],"However,":[36],"due":[37],"distinct":[40],"training":[41,67,118],"objectives,":[42],"GANs":[43],"often":[44],"produce":[45],"features":[46],"that":[47,99],"may":[48],"not":[49],"align":[50],"well":[51],"with":[52,84],"requirements":[54],"downstream":[56],"ASR":[57,89],"systems.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,76],"propose":[63],"an":[64],"improved":[65],"GAN":[66,83],"method.":[68],"While":[69],"generator":[71],"generates":[72],"clean":[73],"embedding,":[75],"replace":[77],"binary-output":[79],"discriminator":[80],"standard":[82],"a":[85,116],"multiclass":[86],"predictor":[87],"(an":[88],"model).":[90],"Extensive":[91],"exper-imental":[92],"results":[93],"on":[94],"real-world":[96],"database":[97],"demonstrate":[98],"our":[100],"proposed":[101],"approach":[102],"outperforms":[103],"traditional":[105],"GAN-based":[106],"has":[109],"potential":[111],"be":[113],"extended":[114],"as":[115],"new":[117],"paradigm":[119],"for":[120],"more":[121],"tasks.":[122]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}