{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A6T5ZOCBLKWHDZ35GYMNE6YFRT","short_pith_number":"pith:A6T5ZOCB","schema_version":"1.0","canonical_sha256":"07a7dcb8415aac71e77d3618d27b058ce12f1d0aee3c88de9b01b3d0fb73adad","source":{"kind":"arxiv","id":"2210.17349","version":3},"attestation_state":"computed","paper":{"title":"Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haiying Wu, Jian Cong, Kun Song, Lei Xie, Ning Jiang, Xinsheng Wang, Yongmao Zhang","submitted_at":"2022-10-31T14:24:10Z","abstract_excerpt":"In current two-stage neural text-to-speech (TTS) paradigm, it is ideal to have a universal neural vocoder, once trained, which is robust to imperfect mel-spectrogram predicted from the acoustic model. To this end, we propose Robust MelGAN vocoder by solving the original multi-band MelGAN's metallic sound problem and increasing its generalization ability. Specifically, we introduce a fine-grained network dropout strategy to the generator. With a specifically designed over-smooth handler which separates speech signal intro periodic and aperiodic components, we only perform network dropout to the"},"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":"2210.17349","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-31T14:24:10Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f4c927d2c054b7faec742ce8ef1dc42cd684b38c8488fc3b35ac0e3840e31294","abstract_canon_sha256":"b2e9a2a6c9a76021a15280761bafbd58041d3867411335927199e660dc849155"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:32.230463Z","signature_b64":"Z8EpOk9Pi3bxQalMdFJFM8vm58HhCRuFWpAvQGLFp+kMp6PAbRklf8jziOSUngERXHTwUPIP92+6KH3+i+qxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07a7dcb8415aac71e77d3618d27b058ce12f1d0aee3c88de9b01b3d0fb73adad","last_reissued_at":"2026-07-05T05:12:32.229963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:32.229963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haiying Wu, Jian Cong, Kun Song, Lei Xie, Ning Jiang, Xinsheng Wang, Yongmao Zhang","submitted_at":"2022-10-31T14:24:10Z","abstract_excerpt":"In current two-stage neural text-to-speech (TTS) paradigm, it is ideal to have a universal neural vocoder, once trained, which is robust to imperfect mel-spectrogram predicted from the acoustic model. To this end, we propose Robust MelGAN vocoder by solving the original multi-band MelGAN's metallic sound problem and increasing its generalization ability. Specifically, we introduce a fine-grained network dropout strategy to the generator. With a specifically designed over-smooth handler which separates speech signal intro periodic and aperiodic components, we only perform network dropout to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17349","kind":"arxiv","version":3},"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/2210.17349/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":"2210.17349","created_at":"2026-07-05T05:12:32.230022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17349v3","created_at":"2026-07-05T05:12:32.230022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17349","created_at":"2026-07-05T05:12:32.230022+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6T5ZOCBLKWH","created_at":"2026-07-05T05:12:32.230022+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6T5ZOCBLKWHDZ35","created_at":"2026-07-05T05:12:32.230022+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6T5ZOCB","created_at":"2026-07-05T05:12:32.230022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT","json":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT.json","graph_json":"https://pith.science/api/pith-number/A6T5ZOCBLKWHDZ35GYMNE6YFRT/graph.json","events_json":"https://pith.science/api/pith-number/A6T5ZOCBLKWHDZ35GYMNE6YFRT/events.json","paper":"https://pith.science/paper/A6T5ZOCB"},"agent_actions":{"view_html":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT","download_json":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT.json","view_paper":"https://pith.science/paper/A6T5ZOCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17349&json=true","fetch_graph":"https://pith.science/api/pith-number/A6T5ZOCBLKWHDZ35GYMNE6YFRT/graph.json","fetch_events":"https://pith.science/api/pith-number/A6T5ZOCBLKWHDZ35GYMNE6YFRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT/action/storage_attestation","attest_author":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT/action/author_attestation","sign_citation":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT/action/citation_signature","submit_replication":"https://pith.science/pith/A6T5ZOCBLKWHDZ35GYMNE6YFRT/action/replication_record"}},"created_at":"2026-07-05T05:12:32.230022+00:00","updated_at":"2026-07-05T05:12:32.230022+00:00"}