{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H6AIBS544NQ2ITJNJ3GGUXQPN7","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":"4e4c7c4a6c919e7066ff1280f0fcf43ab9e24e23aae597e1e21c2cbc1b9e5591","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-04T14:42:12Z","title_canon_sha256":"8b73927b2cfc9b119211ce9c080b68f28f417938ad05db85a38a7aa2c1fe402e"},"schema_version":"1.0","source":{"id":"2506.04013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04013","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04013v1","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04013","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"pith_short_12","alias_value":"H6AIBS544NQ2","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"pith_short_16","alias_value":"H6AIBS544NQ2ITJN","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"pith_short_8","alias_value":"H6AIBS54","created_at":"2026-07-05T11:15:55Z"}],"graph_snapshots":[{"event_id":"sha256:27c8b5c0b3115f4d5fbbe3c695665b825767d9a1579312ff53da5e5c12d6f571","target":"graph","created_at":"2026-07-05T11:15:55Z","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/2506.04013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive voice conversion aims to transfer both speaker identity and expressive attributes from a target speech to a given source speech. In this work, we improve over a self-supervised, non-autoregressive framework with a conditional variational autoencoder, focusing on reducing source timbre leakage and improving linguistic-acoustic disentanglement for better style transfer. To minimize style leakage, we use multilingual discrete speech units for content representation and reinforce embeddings with augmentation-based similarity loss and mix-style layer normalization. To enhance expressivit","authors_text":"Alexander Waibel, Seymanur Akti, Tuan Nam Nguyen","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-04T14:42:12Z","title":"Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04013","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:b3f4f5b992e65408e4cb09fa7e5a6fee2cb24585a6b52b4eee2d0d90221012a2","target":"record","created_at":"2026-07-05T11:15:55Z","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":"4e4c7c4a6c919e7066ff1280f0fcf43ab9e24e23aae597e1e21c2cbc1b9e5591","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-04T14:42:12Z","title_canon_sha256":"8b73927b2cfc9b119211ce9c080b68f28f417938ad05db85a38a7aa2c1fe402e"},"schema_version":"1.0","source":{"id":"2506.04013","kind":"arxiv","version":1}},"canonical_sha256":"3f8080cbbce361a44d2d4ecc6a5e0f6fdc06c6df5563821f28402029ed46e55c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f8080cbbce361a44d2d4ecc6a5e0f6fdc06c6df5563821f28402029ed46e55c","first_computed_at":"2026-07-05T11:15:55.366311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:55.366311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vU3DasxJJq7Cp63AuSfDu5Frb4s/Gg/TiaWo2k2f++oNyjQIOt5SH/ZcsBqgyWuQql1kYl/LPmcUKr53NGYUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:55.367201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3f4f5b992e65408e4cb09fa7e5a6fee2cb24585a6b52b4eee2d0d90221012a2","sha256:27c8b5c0b3115f4d5fbbe3c695665b825767d9a1579312ff53da5e5c12d6f571"],"state_sha256":"a3723fcdb4b3a9a37c0e0801088c1657fe705d951e270f58f425aca239c0a335"}