{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:B3M4CTHG3QBGKCDQ23S7X7QWDZ","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":"1e21150afa313e7e0c02b9703fc17ad946d2da2f3ae0f9aec0c31edccb3cc16c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-12-29T08:56:20Z","title_canon_sha256":"c85b6b761297e5455cd8cf8ec440f76c446f2397ca2564da550ce96c4bbbae9f"},"schema_version":"1.0","source":{"id":"2212.14227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14227","created_at":"2026-07-05T05:29:07Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14227v1","created_at":"2026-07-05T05:29:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14227","created_at":"2026-07-05T05:29:07Z"},{"alias_kind":"pith_short_12","alias_value":"B3M4CTHG3QBG","created_at":"2026-07-05T05:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"B3M4CTHG3QBGKCDQ","created_at":"2026-07-05T05:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"B3M4CTHG","created_at":"2026-07-05T05:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:c9cb29b1fe8249e34dc1a9f686ced86eac1b54e75aa4e75b8ee05288bbf48a65","target":"graph","created_at":"2026-07-05T05:29:07Z","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/2212.14227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity and speech content, a task that still remains challenging. Here, we propose a novel approach to learning disentangled speech representation by transfer learning from style-based text-to-speech (TTS) models. With cycle consistent and adversarial training, the style-based TTS models can perform transcription-guided one-shot VC with high fidelity and similarity. ","authors_text":"Cong Han, Nima Mesgarani, Yinghao Aaron Li","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-12-29T08:56:20Z","title":"StyleTTS-VC: One-Shot Voice Conversion by Knowledge Transfer from Style-Based TTS Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14227","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":"sha256:52f0575be53e79f56ef943ee91b9880b54d097f0d66af4dcf6125eb1821d3e08","target":"record","created_at":"2026-07-05T05:29:07Z","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":"1e21150afa313e7e0c02b9703fc17ad946d2da2f3ae0f9aec0c31edccb3cc16c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-12-29T08:56:20Z","title_canon_sha256":"c85b6b761297e5455cd8cf8ec440f76c446f2397ca2564da550ce96c4bbbae9f"},"schema_version":"1.0","source":{"id":"2212.14227","kind":"arxiv","version":1}},"canonical_sha256":"0ed9c14ce6dc02650870d6e5fbfe161e5468a39d227a9b0dab657f384e42b2b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ed9c14ce6dc02650870d6e5fbfe161e5468a39d227a9b0dab657f384e42b2b8","first_computed_at":"2026-07-05T05:29:07.575744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:07.575744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"unmN8pd4yY8LKLfw/2cq8KcU9wuO+n4OW+ksFbTUBiOyumKwvG0jZFa4fm9BIfWt5ByCcm/n+7YGQhtl0jKnAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:07.576258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.14227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52f0575be53e79f56ef943ee91b9880b54d097f0d66af4dcf6125eb1821d3e08","sha256:c9cb29b1fe8249e34dc1a9f686ced86eac1b54e75aa4e75b8ee05288bbf48a65"],"state_sha256":"1a65b65c7ca9e3b8dcfdfd0b2412a7b90da1113baf19ab2b50ea3384b45569a6"}