{"id":"https://openalex.org/W4392910292","doi":"https://doi.org/10.1109/icassp48485.2024.10445914","title":"Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator","display_name":"Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910292","doi":"https://doi.org/10.1109/icassp48485.2024.10445914"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020693766"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.3415,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48092412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12561","last_page":"12565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9872000217437744,"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":0.9872000217437744,"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":0.9595000147819519,"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/T13579","display_name":"Image and Video Stabilization","score":0.9478999972343445,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.9825513958930969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644059062004089},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7370960712432861},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.6496493816375732},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5655499696731567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48749423027038574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48391467332839966},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44283604621887207},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.42604148387908936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.341028094291687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3407490849494934},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.15410777926445007},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08382269740104675}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9825513958930969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644059062004089},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7370960712432861},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.6496493816375732},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5655499696731567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48749423027038574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48391467332839966},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44283604621887207},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42604148387908936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.341028094291687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3407490849494934},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.15410777926445007},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08382269740104675},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.8100000023841858,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3282004645","display_name":null,"funder_award_id":"JPMJCR","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G4503388090","display_name":null,"funder_award_id":"JPMJCR19A","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2125389028","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2747744257","https://openalex.org/W2769810959","https://openalex.org/W2936774411","https://openalex.org/W2959300817","https://openalex.org/W2963300588","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2992308087","https://openalex.org/W3034720584","https://openalex.org/W3036167779","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3097828251","https://openalex.org/W3099088591","https://openalex.org/W3144035034","https://openalex.org/W3144810982","https://openalex.org/W3161236344","https://openalex.org/W3196468212","https://openalex.org/W3196782138","https://openalex.org/W4210287297","https://openalex.org/W4221152438","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4296070452","https://openalex.org/W4319862245","https://openalex.org/W4372347654","https://openalex.org/W4375868903","https://openalex.org/W4385823165","https://openalex.org/W4385823168","https://openalex.org/W6631190155","https://openalex.org/W6687506355","https://openalex.org/W6745136726","https://openalex.org/W6745930336","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6765775151","https://openalex.org/W6767111847","https://openalex.org/W6769767169","https://openalex.org/W6779093361","https://openalex.org/W6779823529","https://openalex.org/W6780218876","https://openalex.org/W6780507278","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6802838302","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2995777218","https://openalex.org/W3217069185","https://openalex.org/W3049340819","https://openalex.org/W4308928038","https://openalex.org/W4200430540","https://openalex.org/W3141413246","https://openalex.org/W2888032422","https://openalex.org/W4322709305","https://openalex.org/W2808862658","https://openalex.org/W4391899165"],"abstract_inverted_index":{"A":[0,52],"generative":[1],"adversarial":[2,9],"network":[3],"(GAN)-based":[4],"vocoder":[5,48],"trained":[6],"with":[7],"an":[8,97],"discriminator":[10,67,99],"is":[11,55,68],"commonly":[12],"used":[13],"for":[14],"speech":[15,81,115,135,144],"synthesis":[16],"because":[17],"of":[18,33,124],"its":[19],"fast,":[20],"lightweight,":[21],"and":[22,70],"high-quality":[23],"characteristics.":[24],"However,":[25,64],"this":[26,93],"data-driven":[27],"model":[28],"requires":[29],"a":[30,46,65],"large":[31],"amount":[32],"training":[34,59],"data":[35,60,77,139,148],"incurring":[36],"high":[37],"data-collection":[38],"costs.":[39],"This":[40],"fact":[41],"motivates":[42],"us":[43],"to":[44,56,61,72,110,117],"train":[45],"GAN-based":[47],"on":[49],"limited":[50,138],"data.":[51],"promising":[53],"solution":[54],"augment":[57],"the":[58,103,122,125],"avoid":[62],"overfitting.":[63],"standard":[66],"unconditional":[69],"insensitive":[71],"distributional":[73],"changes":[74],"caused":[75],"by":[76],"augmentation.":[78],"Thus,":[79],"augmented":[80],"(which":[82],"can":[83],"be":[84,87],"extraordinary)":[85],"may":[86],"considered":[88],"real":[89],"speech.":[90],"To":[91],"address":[92],"issue,":[94],"we":[95],"propose":[96],"augmentation-conditional":[98],"(AugCondD)":[100],"that":[101,132],"receives":[102],"augmentation":[104,118],"state":[105],"as":[106],"input":[107,114],"in":[108],"addition":[109],"speech,":[111],"thereby":[112],"assessing":[113],"according":[116],"state,":[119],"without":[120],"inhibiting":[121],"learning":[123],"original":[126],"non-augmented":[127],"distribution.":[128],"Experimental":[129],"results":[130],"indicate":[131],"AugCondD":[133],"improves":[134],"quality":[136,145],"under":[137,146],"conditions":[140],"while":[141],"achieving":[142],"comparable":[143],"sufficient":[147],"conditions.":[149],"<sup":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}