{"id":"https://openalex.org/W3198234802","doi":"https://doi.org/10.21437/interspeech.2021-41","title":"GAN Vocoder: Multi-Resolution Discriminator Is All You Need","display_name":"GAN Vocoder: Multi-Resolution Discriminator Is All You Need","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198234802","doi":"https://doi.org/10.21437/interspeech.2021-41","mag":"3198234802"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-41","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5076529957","display_name":"Jaeseong You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaeseong You","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057812168","display_name":"Dal-Hyun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dalhyun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081937563","display_name":"Gyuhyeon Nam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyuhyeon Nam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070443803","display_name":"Geumbyeol Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geumbyeol Hwang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008455163","display_name":"Gyeongsu Chae","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyeongsu Chae","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3789,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90636089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2177","last_page":"2181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9969000220298767,"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":0.9911999702453613,"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":0.9263539910316467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7784565687179565},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.6256199479103088},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6157341003417969},{"id":"https://openalex.org/keywords/competitor-analysis","display_name":"Competitor analysis","score":0.4705165922641754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4364606738090515},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4198175072669983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3771064281463623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11170440912246704},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10552570223808289},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0880071222782135}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9263539910316467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784565687179565},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.6256199479103088},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6157341003417969},{"id":"https://openalex.org/C127576917","wikidata":"https://www.wikidata.org/wiki/Q624630","display_name":"Competitor analysis","level":2,"score":0.4705165922641754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4364606738090515},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4198175072669983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3771064281463623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11170440912246704},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10552570223808289},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0880071222782135},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-41","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W1608433645","https://openalex.org/W2964074194"],"abstract_inverted_index":{"Several":[0],"of":[1,23],"the":[2,32,39,44,57],"latest":[3],"GAN-based":[4],"vocoders":[5],"show":[6],"remarkable":[7],"achievements,":[8],"outperforming":[9],"autoregressive":[10],"and":[11,17,80],"flow-based":[12],"competitors":[13],"in":[14,47],"both":[15],"qualitative":[16],"quantitative":[18],"measures":[19,74],"while":[20],"synthesizing":[21],"orders":[22],"magnitude":[24],"faster.":[25],"In":[26],"this":[27],"work,":[28],"we":[29],"hypothesize":[30],"that":[31],"common":[33],"factor":[34],"underlying":[35],"their":[36,85],"success":[37],"is":[38],"multi-resolution":[40,68],"discriminating":[41,69],"framework,":[42],"not":[43,88],"minute":[45],"details":[46],"architecture,":[48],"loss":[49],"function,":[50],"or":[51],"training":[52],"strategy.":[53],"We":[54],"experimentally":[55],"test":[56],"hypothesis":[58],"by":[59],"evaluating":[60],"six":[61],"different":[62],"generators":[63],"paired":[64],"with":[65,75],"one":[66,91],"shared":[67],"framework.":[70],"For":[71],"all":[72,82],"evaluative":[73],"respect":[76],"to":[77],"text-to-speech":[78],"syntheses":[79],"for":[81],"perceptual":[83],"metrics,":[84],"performances":[86],"are":[87],"distinguishable":[89],"from":[90],"another,":[92],"which":[93],"supports":[94],"our":[95],"hypothesis.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}