{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HQVZWY2OOHCFGJ7OWN6CITL7LY","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":"311a096fb56cb5065f684858cde52fc7e90d1d0013d3c46a2c7353162edc97f1","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-02T09:07:33Z","title_canon_sha256":"2acc95b438ea484b7b06e97c043c6f43168df2be2e26e28c5e49df6427325bdc"},"schema_version":"1.0","source":{"id":"2410.01350","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01350","created_at":"2026-07-05T09:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01350v2","created_at":"2026-07-05T09:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01350","created_at":"2026-07-05T09:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"HQVZWY2OOHCF","created_at":"2026-07-05T09:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"HQVZWY2OOHCFGJ7O","created_at":"2026-07-05T09:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"HQVZWY2O","created_at":"2026-07-05T09:59:19Z"}],"graph_snapshots":[{"event_id":"sha256:866811488d5a2b8f2fbfb84cf02c3d67753b50a9a070c898646a72b24e2ca0b9","target":"graph","created_at":"2026-07-05T09:59:19Z","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/2410.01350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive zero-shot voice conversion (VC) is a critical and challenging task that aims to transform the source timbre into an arbitrary unseen speaker while preserving the original content and expressive qualities. Despite recent progress in zero-shot VC, there remains considerable potential for improvements in speaker similarity and speech naturalness. Moreover, existing zero-shot VC systems struggle to fully reproduce paralinguistic information in highly expressive speech, such as breathing, crying, and emotional nuances, limiting their practical applicability. To address these issues, we p","authors_text":"Hongbin Zhou, Jianhao Ye, Jianjun Zhao, Jixun Yao, Lei Ma, Lei Xie, Xiang Zhang, Yuguang Yang, Yu Pan","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-02T09:07:33Z","title":"Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01350","kind":"arxiv","version":2},"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":"sha256:3d28755d42f9b03b6faa9813f45a5ef5b02aff4a61ea9484bf2408024c651e00","target":"record","created_at":"2026-07-05T09:59:19Z","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":"311a096fb56cb5065f684858cde52fc7e90d1d0013d3c46a2c7353162edc97f1","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-02T09:07:33Z","title_canon_sha256":"2acc95b438ea484b7b06e97c043c6f43168df2be2e26e28c5e49df6427325bdc"},"schema_version":"1.0","source":{"id":"2410.01350","kind":"arxiv","version":2}},"canonical_sha256":"3c2b9b634e71c45327eeb37c244d7f5e2c9a844797625fd51e609ac5d5ba0f93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c2b9b634e71c45327eeb37c244d7f5e2c9a844797625fd51e609ac5d5ba0f93","first_computed_at":"2026-07-05T09:59:19.693051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:19.693051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xYMI7Ajf01Ah+CTS8zABSzPSfdeh2xW8zmjpGqMOaWQfMdztafU81TqR1kVje6C3JoZgcNpLUx3Zegs1VMeVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:19.693489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01350","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d28755d42f9b03b6faa9813f45a5ef5b02aff4a61ea9484bf2408024c651e00","sha256:866811488d5a2b8f2fbfb84cf02c3d67753b50a9a070c898646a72b24e2ca0b9"],"state_sha256":"fe8bd2fe9b26a2324747221892cfd55d76c2bcb15011e8e22e5b24f6d5f5a08d"}