{"id":"https://openalex.org/W7135241571","doi":"https://doi.org/10.48550/arxiv.2603.11678","title":"RAF: Relativistic Adversarial Feedback For Universal Speech Synthesis","display_name":"RAF: Relativistic Adversarial Feedback For Universal Speech Synthesis","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135241571","doi":"https://doi.org/10.48550/arxiv.2603.11678"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11678","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.11678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075606753","display_name":"Yongjoon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Yongjoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128969432","display_name":"Jung-Woo Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Jung-Woo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.8066999912261963,"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":0.8066999912261963,"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":0.036400001496076584,"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":0.0357000008225441,"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/adversarial-system","display_name":"Adversarial system","score":0.728600025177002},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6205999851226807},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5853999853134155},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4747999906539917},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.39910000562667847},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3779999911785126},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.351500004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585999965667725},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.728600025177002},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6205999851226807},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5690000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3619000017642975},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11678","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.11678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11678","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7336475253105164}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"Relativistic":[2],"Adversarial":[3],"Feedback":[4],"(RAF),":[5],"a":[6,123],"novel":[7],"training":[8,30,78,124],"objective":[9,90],"for":[10,67,126],"GAN":[11,24,127],"vocoders":[12,25],"that":[13],"improves":[14],"in-domain":[15],"fidelity":[16],"and":[17,69,91],"generalization":[18],"to":[19,34,48,58,72],"unseen":[20],"scenarios.":[21],"Although":[22],"modern":[23],"employ":[26],"advanced":[27],"architectures,":[28],"their":[29],"objectives":[31],"often":[32],"fail":[33],"promote":[35],"generalizable":[36],"representations.":[37,61],"RAF":[38,121],"addresses":[39],"this":[40],"problem":[41],"by":[42],"leveraging":[43],"speech":[44],"self-supervised":[45],"learning":[46],"models":[47],"assist":[49],"discriminators":[50],"in":[51,88,105],"evaluating":[52],"sample":[53],"quality,":[54],"encouraging":[55],"the":[56,74,77,98,102,112,118],"generator":[57],"learn":[59],"richer":[60],"Furthermore,":[62],"we":[63],"utilize":[64],"relativistic":[65],"pairing":[66],"real":[68],"fake":[70],"waveforms":[71],"improve":[73],"modeling":[75],"of":[76,111,120],"data":[79],"distribution.":[80],"Experiments":[81],"across":[82],"multiple":[83],"datasets":[84],"show":[85],"consistent":[86],"gains":[87],"both":[89],"subjective":[92],"metrics":[93],"on":[94],"GAN-based":[95],"vocoders.":[96,128],"Importantly,":[97],"RAF-trained":[99],"BigVGAN-base":[100],"outperforms":[101],"LSGAN-trained":[103],"BigVGAN":[104],"perceptual":[106],"quality":[107],"using":[108],"only":[109],"12\\%":[110],"parameters.":[113],"Comparative":[114],"studies":[115],"further":[116],"confirm":[117],"effectiveness":[119],"as":[122],"framework":[125]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-14T00:00:00"}