{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:34HMPABIILSBZGGXI5Q6IMQD7R","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":"150c3b3eeb924c72c999004ecde73a4c6d7e3ccf27c7bc9ef92a1d76e56440c3","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-29T15:02:22Z","title_canon_sha256":"4b06ed75f021293217921823b9b5f5120e8d0e83e7e5a2d8435c06fefcf6d3c5"},"schema_version":"1.0","source":{"id":"2306.17005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17005","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17005v1","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17005","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_12","alias_value":"34HMPABIILSB","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_16","alias_value":"34HMPABIILSBZGGX","created_at":"2026-07-05T06:26:12Z"},{"alias_kind":"pith_short_8","alias_value":"34HMPABI","created_at":"2026-07-05T06:26:12Z"}],"graph_snapshots":[{"event_id":"sha256:53306c573abc4165489046cddba885176d9b3d712d5dd799279877e304281277","target":"graph","created_at":"2026-07-05T06:26:12Z","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/2306.17005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of Automatic Voice Over (AVO) is to generate speech in sync with a silent video given its text script. Recent AVO frameworks built upon text-to-speech synthesis (TTS) have shown impressive results. However, the current AVO learning objective of acoustic feature reconstruction brings in indirect supervision for inter-modal alignment learning, thus limiting the synchronization performance and synthetic speech quality. To this end, we propose a novel AVO method leveraging the learning objective of self-supervised discrete speech unit prediction, which not only provides more direct superv","authors_text":"Berrak Sisman, Haizhou Li, Junchen Lu, Mingyang Zhang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-29T15:02:22Z","title":"High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17005","kind":"arxiv","version":1},"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":"sha256:88475c99d4eb09db95d028a6e59a753a5b59eeaf4aac96ba75cbf499b70873d1","target":"record","created_at":"2026-07-05T06:26:12Z","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":"150c3b3eeb924c72c999004ecde73a4c6d7e3ccf27c7bc9ef92a1d76e56440c3","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-29T15:02:22Z","title_canon_sha256":"4b06ed75f021293217921823b9b5f5120e8d0e83e7e5a2d8435c06fefcf6d3c5"},"schema_version":"1.0","source":{"id":"2306.17005","kind":"arxiv","version":1}},"canonical_sha256":"df0ec7802842e41c98d74761e43203fc4959b27cccf655f1c1b0b549d523bd0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df0ec7802842e41c98d74761e43203fc4959b27cccf655f1c1b0b549d523bd0c","first_computed_at":"2026-07-05T06:26:12.136463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:12.136463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0svNWuF6fI3Ds1UBsj+xPOk5GijKUzhbs2xxKz7Hd6EBL/D/tOVvWUF1b16s5K8+/Mdz1fbfSier8mOPAMTRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:12.136936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88475c99d4eb09db95d028a6e59a753a5b59eeaf4aac96ba75cbf499b70873d1","sha256:53306c573abc4165489046cddba885176d9b3d712d5dd799279877e304281277"],"state_sha256":"0b8f5b828f76613bdaec1727ecb9b87da3fdc6728002a4422a72b3887831fe3c"}