{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MKR5ZNO5WLRV5EBET2GVLP35WO","short_pith_number":"pith:MKR5ZNO5","schema_version":"1.0","canonical_sha256":"62a3dcb5ddb2e35e90249e8d55bf7db38463350860caa460f7816663291844f6","source":{"kind":"arxiv","id":"2010.05646","version":2},"attestation_state":"computed","paper":{"title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jaehyeon Kim, Jaekyoung Bae, Jungil Kong","submitted_at":"2020-10-12T12:33:43Z","abstract_excerpt":"Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of autoregressive and flow-based generative models. In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. As speech audio consists of sinusoidal signals with various periods, we demonstrate that modeling periodic patterns of an audio is crucial for enhancing sample quality. A subjective human evaluation (mean opini"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.05646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-10-12T12:33:43Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"b2ad5ad8057d9e5fcd780954bb11b55d949dccb015d3cb3d86510dfd93d4dc27","abstract_canon_sha256":"0c049b0282214176adb6fa4220526aa83724fdd2c1cc8f634fcdc2b8033d3c7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:30.924655Z","signature_b64":"DyDJKfbjkoJZwkO8lRLFSrezc9ACKY8zoiwMtP2RkgLU0hJQb706vs3A2WEgDNb2lrxiyLXaVDQG++ZW4FrtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62a3dcb5ddb2e35e90249e8d55bf7db38463350860caa460f7816663291844f6","last_reissued_at":"2026-07-05T01:45:30.924205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:30.924205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jaehyeon Kim, Jaekyoung Bae, Jungil Kong","submitted_at":"2020-10-12T12:33:43Z","abstract_excerpt":"Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of autoregressive and flow-based generative models. In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. As speech audio consists of sinusoidal signals with various periods, we demonstrate that modeling periodic patterns of an audio is crucial for enhancing sample quality. A subjective human evaluation (mean opini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05646","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.05646/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.05646","created_at":"2026-07-05T01:45:30.924259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.05646v2","created_at":"2026-07-05T01:45:30.924259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05646","created_at":"2026-07-05T01:45:30.924259+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKR5ZNO5WLRV","created_at":"2026-07-05T01:45:30.924259+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKR5ZNO5WLRV5EBE","created_at":"2026-07-05T01:45:30.924259+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKR5ZNO5","created_at":"2026-07-05T01:45:30.924259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29531","citing_title":"Audio Deepfake Detection with Half-Truth Localisation Using Cross-Attentive Feature Fusion","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03233","citing_title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27273","citing_title":"Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02496","citing_title":"Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO","json":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO.json","graph_json":"https://pith.science/api/pith-number/MKR5ZNO5WLRV5EBET2GVLP35WO/graph.json","events_json":"https://pith.science/api/pith-number/MKR5ZNO5WLRV5EBET2GVLP35WO/events.json","paper":"https://pith.science/paper/MKR5ZNO5"},"agent_actions":{"view_html":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO","download_json":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO.json","view_paper":"https://pith.science/paper/MKR5ZNO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.05646&json=true","fetch_graph":"https://pith.science/api/pith-number/MKR5ZNO5WLRV5EBET2GVLP35WO/graph.json","fetch_events":"https://pith.science/api/pith-number/MKR5ZNO5WLRV5EBET2GVLP35WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO/action/storage_attestation","attest_author":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO/action/author_attestation","sign_citation":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO/action/citation_signature","submit_replication":"https://pith.science/pith/MKR5ZNO5WLRV5EBET2GVLP35WO/action/replication_record"}},"created_at":"2026-07-05T01:45:30.924259+00:00","updated_at":"2026-07-05T01:45:30.924259+00:00"}