{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SOE42A6ZO2OUSQ6IYNXMRXADDC","short_pith_number":"pith:SOE42A6Z","schema_version":"1.0","canonical_sha256":"9389cd03d9769d4943c8c36ec8dc03189162cd574f9afe16762dbac39141b1c0","source":{"kind":"arxiv","id":"2206.04658","version":2},"attestation_state":"computed","paper":{"title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Boris Ginsburg, Bryan Catanzaro, Sang-gil Lee, Sungroh Yoon, Wei Ping","submitted_at":"2022-06-09T17:56:10Z","abstract_excerpt":"Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across various recording environments. In this work, we present BigVGAN, a universal vocoder that generalizes well for various out-of-distribution scenarios without fine-tuning. We introduce periodic activation function and anti-aliased representation into the GAN generator, which brings the desired inductive bias for audio synthesis and significantly improves audio qual"},"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":"2206.04658","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-06-09T17:56:10Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"6be55ec8743851629f5a8231a019aacc5e487bf5697ce13836990e261c9170c7","abstract_canon_sha256":"230212724a3da2e9f1cff6a0939f133e735444410044161d995e80e12786693a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:25.604933Z","signature_b64":"3X1/TXXZevcXT0QjD7jZhf76z1mQ2FeXOVWnXP13lyIEzYbEA9agUHJlm4+3Ynk77KPzq+qaxUKTL1lM1aNhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9389cd03d9769d4943c8c36ec8dc03189162cd574f9afe16762dbac39141b1c0","last_reissued_at":"2026-07-05T05:42:25.604493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:25.604493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Boris Ginsburg, Bryan Catanzaro, Sang-gil Lee, Sungroh Yoon, Wei Ping","submitted_at":"2022-06-09T17:56:10Z","abstract_excerpt":"Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across various recording environments. In this work, we present BigVGAN, a universal vocoder that generalizes well for various out-of-distribution scenarios without fine-tuning. We introduce periodic activation function and anti-aliased representation into the GAN generator, which brings the desired inductive bias for audio synthesis and significantly improves audio qual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04658","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/2206.04658/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":"2206.04658","created_at":"2026-07-05T05:42:25.604558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04658v2","created_at":"2026-07-05T05:42:25.604558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04658","created_at":"2026-07-05T05:42:25.604558+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOE42A6ZO2OU","created_at":"2026-07-05T05:42:25.604558+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOE42A6ZO2OUSQ6I","created_at":"2026-07-05T05:42:25.604558+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOE42A6Z","created_at":"2026-07-05T05:42:25.604558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20101","citing_title":"Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20101","citing_title":"Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03455","citing_title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31128","citing_title":"UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26672","citing_title":"Can We Hear from Events? Generating Speech from Event Camera","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29531","citing_title":"Audio Deepfake Detection with Half-Truth Localisation Using Cross-Attentive Feature Fusion","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17085","citing_title":"Taming Audio VAEs via Target-KL Regularization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18749","citing_title":"WavFlow: Audio Generation in Waveform Space","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15831","citing_title":"Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2505.24437","citing_title":"SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01284","citing_title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17986","citing_title":"Latent Fourier Transform","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC","json":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC.json","graph_json":"https://pith.science/api/pith-number/SOE42A6ZO2OUSQ6IYNXMRXADDC/graph.json","events_json":"https://pith.science/api/pith-number/SOE42A6ZO2OUSQ6IYNXMRXADDC/events.json","paper":"https://pith.science/paper/SOE42A6Z"},"agent_actions":{"view_html":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC","download_json":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC.json","view_paper":"https://pith.science/paper/SOE42A6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04658&json=true","fetch_graph":"https://pith.science/api/pith-number/SOE42A6ZO2OUSQ6IYNXMRXADDC/graph.json","fetch_events":"https://pith.science/api/pith-number/SOE42A6ZO2OUSQ6IYNXMRXADDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC/action/storage_attestation","attest_author":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC/action/author_attestation","sign_citation":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC/action/citation_signature","submit_replication":"https://pith.science/pith/SOE42A6ZO2OUSQ6IYNXMRXADDC/action/replication_record"}},"created_at":"2026-07-05T05:42:25.604558+00:00","updated_at":"2026-07-05T05:42:25.604558+00:00"}