{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BFJDTHBUUQGALCBZ73LPKQEQAN","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":"56f20d670284dd9cdbf073df4ab03136e9aafcbeb642a2eb1e8f25a2fa0bd3d2","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-04T12:23:17Z","title_canon_sha256":"dca072159bcceedc01ed534013e807bc45decfc5a61ca46a11d8c4960520bfdf"},"schema_version":"1.0","source":{"id":"2411.02026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02026","created_at":"2026-07-05T11:51:18Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02026v2","created_at":"2026-07-05T11:51:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02026","created_at":"2026-07-05T11:51:18Z"},{"alias_kind":"pith_short_12","alias_value":"BFJDTHBUUQGA","created_at":"2026-07-05T11:51:18Z"},{"alias_kind":"pith_short_16","alias_value":"BFJDTHBUUQGALCBZ","created_at":"2026-07-05T11:51:18Z"},{"alias_kind":"pith_short_8","alias_value":"BFJDTHBU","created_at":"2026-07-05T11:51:18Z"}],"graph_snapshots":[{"event_id":"sha256:c440d246f66e6f4b4db1ef6b5519b1c75695e58ab610f36b082af6bbccfa5d7e","target":"graph","created_at":"2026-07-05T11:51:18Z","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/2411.02026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in zero-shot voice conversion (VC), achieving speaker similarity and naturalness comparable to ground-truth recordings remains a significant challenge. In this letter, we propose CTEFM-VC, a zero-shot VC framework that integrates content-aware timbre ensemble modeling with conditional flow matching. Specifically, CTEFM-VC decouples utterances into content and timbre representations and leverages a conditional flow matching model to reconstruct the Mel-spectrogram of the source speech. To enhance its timbre modeling capability and naturalness of generated speech, we firs","authors_text":"Jianjun Zhao, Jixun Yao, Lei Ma, 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":"2024-11-04T12:23:17Z","title":"Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02026","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:ce9f1f9ae350dca5662c09266dc12c252cf2f33e6f817d53c154778a26d69d32","target":"record","created_at":"2026-07-05T11:51:18Z","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":"56f20d670284dd9cdbf073df4ab03136e9aafcbeb642a2eb1e8f25a2fa0bd3d2","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-04T12:23:17Z","title_canon_sha256":"dca072159bcceedc01ed534013e807bc45decfc5a61ca46a11d8c4960520bfdf"},"schema_version":"1.0","source":{"id":"2411.02026","kind":"arxiv","version":2}},"canonical_sha256":"0952399c34a40c058839fed6f5409003669c4db5eca6c536beca2364e67b6c73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0952399c34a40c058839fed6f5409003669c4db5eca6c536beca2364e67b6c73","first_computed_at":"2026-07-05T11:51:18.721790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:18.721790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Paz1FBs5tTYDmxiybrcgpUEm6byOqN8v0bXp+1mM3KF17xi6N6PVTWPyHt/2kuA+xC0T+RNkUB76zbmi7RlRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:18.722271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce9f1f9ae350dca5662c09266dc12c252cf2f33e6f817d53c154778a26d69d32","sha256:c440d246f66e6f4b4db1ef6b5519b1c75695e58ab610f36b082af6bbccfa5d7e"],"state_sha256":"a1a7cce785654d6729d73a032989b6ec7abbcd41f78ce80e0030669a6092660b"}