{"id":"https://openalex.org/W4372347654","doi":"https://doi.org/10.1109/icassp49357.2023.10096288","title":"Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis","display_name":"Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347654","doi":"https://doi.org/10.1109/icassp49357.2023.10096288"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096288","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, 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,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101792863","display_name":"Shogo Seki","orcid":"https://orcid.org/0000-0001-8284-188X"},"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":"Shogo Seki","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020693766"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.3986,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84490521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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":0.9888424873352051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7439201474189758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6695220470428467},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.649224042892456},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5593351721763611},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5366835594177246},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5184870958328247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4770183563232422},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4422321021556854},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4107182025909424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34076839685440063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32993650436401367},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12430274486541748},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.12290605902671814},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1054760217666626},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.06452751159667969}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9888424873352051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439201474189758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6695220470428467},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.649224042892456},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5593351721763611},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5366835594177246},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5184870958328247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4770183563232422},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4422321021556854},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4107182025909424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34076839685440063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32993650436401367},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12430274486541748},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.12290605902671814},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1054760217666626},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.06452751159667969},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096288","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"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":62,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2194775991","https://openalex.org/W2202109488","https://openalex.org/W2284050935","https://openalex.org/W2502312327","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2747744257","https://openalex.org/W2765486990","https://openalex.org/W2769810959","https://openalex.org/W2785678896","https://openalex.org/W2792263949","https://openalex.org/W2908510526","https://openalex.org/W2945478979","https://openalex.org/W2963300588","https://openalex.org/W2963452667","https://openalex.org/W2963975282","https://openalex.org/W2964167449","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3035687950","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3095936335","https://openalex.org/W3097828251","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3144035034","https://openalex.org/W3161236344","https://openalex.org/W3162512456","https://openalex.org/W3169905056","https://openalex.org/W4221152438","https://openalex.org/W4287761884","https://openalex.org/W4294619240","https://openalex.org/W4296070452","https://openalex.org/W4298580827","https://openalex.org/W4302765731","https://openalex.org/W4320013936","https://openalex.org/W6639824700","https://openalex.org/W6695676441","https://openalex.org/W6724804524","https://openalex.org/W6735429107","https://openalex.org/W6745289305","https://openalex.org/W6748409065","https://openalex.org/W6748582592","https://openalex.org/W6749927861","https://openalex.org/W6751512325","https://openalex.org/W6753855596","https://openalex.org/W6757817989","https://openalex.org/W6762533536","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2366944513","https://openalex.org/W3217069185","https://openalex.org/W2784931967","https://openalex.org/W4293400715","https://openalex.org/W3049340819","https://openalex.org/W4308928038","https://openalex.org/W4200430540","https://openalex.org/W3141413246","https://openalex.org/W3112293331","https://openalex.org/W2808862658"],"abstract_inverted_index":{"In":[0],"speech":[1,25,57,146,185],"synthesis,":[2],"a":[3,9,14,17,88,93,108,111,137,164,188,203],"generative":[4],"adversarial":[5],"network":[6],"(GAN),":[7],"training":[8],"generator":[10,138],"(speech":[11],"synthesizer)":[12],"and":[13,40,72,129,169,192,202,207],"discriminator":[15,97,102,197,212],"in":[16,34,68,79,110,200,215],"min-max":[18],"game,":[19],"is":[20,31,92,103],"widely":[21],"used":[22,33,199,214],"to":[23,47,58,76,147,151,163],"improve":[24],"quality.":[26],"An":[27],"ensemble":[28],"of":[29,82],"discriminators":[30,54],"commonly":[32],"recent":[35],"neural":[36,166],"vocoders":[37],"(e.g.,":[38,45],"HiFi-GAN)":[39],"end-to-end":[41,171],"text-to-speech":[42],"(TTS)":[43],"systems":[44],"VITS)":[46],"scrutinize":[48],"waveforms":[49],"from":[50],"multiple":[51],"perspectives.":[52],"Such":[53],"allow":[55],"synthesized":[56,145],"adequately":[59],"approach":[60],"real":[61,153],"speech;":[62],"however,":[63],"they":[64],"require":[65],"an":[66,127,170],"increase":[67,78],"the":[69,77,80,115,119,144,152,156,158,179],"model":[70],"size":[71],"computation":[73],"time":[74],"according":[75],"number":[81],"discriminators.":[83],"Alternatively,":[84],"this":[85],"study":[86],"proposes":[87],"Wave-U-Net":[89,99],"discriminator,":[90],"which":[91],"single":[94],"but":[95],"expressive":[96],"with":[98,114,131,139,187],"architecture.":[100],"This":[101,134],"unique;":[104],"it":[105],"can":[106,182],"assess":[107],"waveform":[109],"sample-wise":[112],"manner":[113],"same":[116],"resolution":[117],"as":[118],"input":[120],"signal,":[121],"while":[122],"extracting":[123],"multilevel":[124],"features":[125],"via":[126],"encoder":[128],"decoder":[130],"skip":[132],"connections.":[133],"architecture":[135],"provides":[136],"sufficiently":[140],"rich":[141],"information":[142],"for":[143],"be":[148],"closely":[149],"matched":[150],"speech.":[154],"During":[155],"experiments,":[157],"proposed":[159,180],"ideas":[160],"were":[161],"applied":[162],"representative":[165],"vocoder":[167],"(HiFi-GAN)":[168],"TTS":[172],"system":[173],"(VITS).":[174],"The":[175],"results":[176],"demonstrate":[177],"that":[178],"models":[181],"achieve":[183],"comparable":[184],"quality":[186],"2.31":[189],"times":[190,194,205,209],"faster":[191,206],"14.5":[193],"more":[195,210],"lightweight":[196,211],"when":[198,213],"HiFi-GAN":[201],"1.90":[204],"9.62":[208],"VITS.<sup":[216],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[217],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}