{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JCHDPSN32SQI64DHVG4ZLPUCNZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"69a8202121c7b42889d02a94374fe8244e197fd7cafa908104e22d15748d365e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-04-02T05:28:48Z","title_canon_sha256":"1d97380d4668253a28ea0d43d139e3a885eae6a862314adff23c8735207312ef"},"schema_version":"1.0","source":{"id":"2204.00768","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00768","created_at":"2026-07-05T09:24:49Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00768v4","created_at":"2026-07-05T09:24:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00768","created_at":"2026-07-05T09:24:49Z"},{"alias_kind":"pith_short_12","alias_value":"JCHDPSN32SQI","created_at":"2026-07-05T09:24:49Z"},{"alias_kind":"pith_short_16","alias_value":"JCHDPSN32SQI64DH","created_at":"2026-07-05T09:24:49Z"},{"alias_kind":"pith_short_8","alias_value":"JCHDPSN3","created_at":"2026-07-05T09:24:49Z"}],"graph_snapshots":[{"event_id":"sha256:654bb927ba0b5ee43469759caf6d0261efc343a26e69c7432a605457a81c63bc","target":"graph","created_at":"2026-07-05T09:24:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.00768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The mainstream neural text-to-speech(TTS) pipeline is a cascade system, including an acoustic model(AM) that predicts acoustic feature from the input transcript and a vocoder that generates waveform according to the given acoustic feature. However, the acoustic feature in current TTS systems is typically mel-spectrogram, which is highly correlated along both time and frequency axes in a complicated way, leading to a great difficulty for the AM to predict. Although high-fidelity audio can be generated by recent neural vocoders from ground-truth(GT) mel-spectrogram, the gap between the GT and th","authors_text":"Chenpeng Du, Kai Yu, Xie Chen, Yiwei Guo","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-04-02T05:28:48Z","title":"VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00768","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:98335848ae5d8eb4ea44584661f122c54727bfc66457b860e27145f271d54bcc","target":"record","created_at":"2026-07-05T09:24:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"69a8202121c7b42889d02a94374fe8244e197fd7cafa908104e22d15748d365e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-04-02T05:28:48Z","title_canon_sha256":"1d97380d4668253a28ea0d43d139e3a885eae6a862314adff23c8735207312ef"},"schema_version":"1.0","source":{"id":"2204.00768","kind":"arxiv","version":4}},"canonical_sha256":"488e37c9bbd4a08f7067a9b995be826e6a89bf3709cc839725b629b3cd1fe77c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"488e37c9bbd4a08f7067a9b995be826e6a89bf3709cc839725b629b3cd1fe77c","first_computed_at":"2026-07-05T09:24:49.465535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:49.465535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X+zGq9eSgntwxpFBQICFLXiVxEu/oplRcetHoZwSPBvBJ8AxfBPzHGBCUhuMyDYSQ5m9s4G6hHHYZj5O8AaUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:49.466034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00768","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98335848ae5d8eb4ea44584661f122c54727bfc66457b860e27145f271d54bcc","sha256:654bb927ba0b5ee43469759caf6d0261efc343a26e69c7432a605457a81c63bc"],"state_sha256":"ddb213e673a5cc297cbe9174681748a96377f05a747b1931e4b4494db7813ea8"}