{"id":"https://openalex.org/W3017109760","doi":"https://doi.org/10.1109/icaiic48513.2020.9065067","title":"Audio Translation with Conditional Generative Adversarial Networks","display_name":"Audio Translation with Conditional Generative Adversarial Networks","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3017109760","doi":"https://doi.org/10.1109/icaiic48513.2020.9065067","mag":"3017109760"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic48513.2020.9065067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic48513.2020.9065067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5109265497","display_name":"Ahmad Moussa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ahmad Moussa","raw_affiliation_strings":["Graduate School of Fundamental Science and Eng., Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Fundamental Science and Eng., Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025914451","display_name":"Hiroshi Watanabe","orcid":"https://orcid.org/0000-0003-1557-3015"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Watanabe","raw_affiliation_strings":["Graduate School of Fundamental Science and Eng., Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Fundamental Science and Eng., Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109265497"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03535221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1604 4382","issue":null,"first_page":"438","last_page":"442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8016619682312012},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6565720438957214},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.6396017074584961},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.627913773059845},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5245400071144104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.478641152381897},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47293758392333984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46857261657714844},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43632155656814575},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.42955464124679565},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3445129990577698},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2181183397769928},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09450674057006836},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08167695999145508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016619682312012},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6565720438957214},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6396017074584961},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.627913773059845},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5245400071144104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.478641152381897},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47293758392333984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46857261657714844},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43632155656814575},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.42955464124679565},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3445129990577698},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2181183397769928},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09450674057006836},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08167695999145508},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic48513.2020.9065067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic48513.2020.9065067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W2064675550","https://openalex.org/W2076063813","https://openalex.org/W2095705004","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2127836593","https://openalex.org/W2194775991","https://openalex.org/W2339754110","https://openalex.org/W2423557781","https://openalex.org/W2519091744","https://openalex.org/W2606176153","https://openalex.org/W2949117887","https://openalex.org/W2949382160","https://openalex.org/W2949650786","https://openalex.org/W2951535099","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963636093","https://openalex.org/W2963840672","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W3207342693","https://openalex.org/W4320013936","https://openalex.org/W6639824700","https://openalex.org/W6674330103","https://openalex.org/W6696085341","https://openalex.org/W6735429107","https://openalex.org/W7023653924"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W2964074194","https://openalex.org/W4224918993"],"abstract_inverted_index":{"This":[0,74,92],"paper":[1],"explores":[2],"the":[3,64,94,116],"applicability":[4],"of":[5,21,67,97,118],"conditional":[6,60],"generative":[7],"adversarial":[8],"networks":[9],"in":[10,46],"audio-to-audio":[11],"translation":[12],"problems":[13],"and":[14,82],"proposes":[15],"a":[16,59,71,111],"neural":[17],"network":[18],"architecture":[19,62,75],"capable":[20],"doing":[22],"so.":[23],"Recent":[24],"advances":[25],"have":[26],"shown":[27],"that":[28,51],"causal":[29],"convolutions":[30,57],"can":[31,76],"be":[32,78],"effective":[33],"for":[34,115],"modeling":[35],"raw":[36,68],"audio":[37,69,100],"when":[38],"their":[39],"kernel":[40],"is":[41],"dilated":[42],"by":[43],"many":[44],"factors,":[45],"contrast":[47],"to":[48,80,88],"previous":[49],"techniques":[50],"utilized":[52],"recurrent":[53],"approaches.":[54],"Embedding":[55],"such":[56],"within":[58],"GAN":[61],"allows":[63],"targeted":[65],"generation":[66],"given":[70],"certain":[72,84],"input.":[73],"then":[77],"used":[79],"learn":[81],"simulate":[83],"translative":[85],"operations":[86],"applied":[87],"an":[89],"input":[90],"signal.":[91],"creates":[93],"defined":[95],"problem":[96],"converting":[98],"one":[99],"signal":[101],"into":[102],"another,":[103],"which":[104],"has":[105],"different":[106],"characteristics.":[107],"We":[108],"also":[109],"propose":[110],"novel":[112],"discriminator":[113],"structure":[114],"evaluation":[117],"generated":[119],"audio.":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}