{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z7QANFVV5M2S7GDXTIEDMI5NGG","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":"60a9b8bd9d6126d951a4e47e0feb633977db0d2e6a271e7ba62cb189cc3a2b67","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-30T02:23:37Z","title_canon_sha256":"27cd83350ecbe7152483507fce0418ffbbc1303b5eb47cef890c3acc115d956d"},"schema_version":"1.0","source":{"id":"2404.19212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19212","created_at":"2026-07-05T08:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19212v1","created_at":"2026-07-05T08:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19212","created_at":"2026-07-05T08:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"Z7QANFVV5M2S","created_at":"2026-07-05T08:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"Z7QANFVV5M2S7GDX","created_at":"2026-07-05T08:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"Z7QANFVV","created_at":"2026-07-05T08:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:516df287dba8c9c21e89d44f161c0959231f58c15486ce03b33b400a20ed13b3","target":"graph","created_at":"2026-07-05T08:13:40Z","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/2404.19212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted bottleneck features which can not achieve sufficient information disentangling, while pitch and rhythm may still be mixed together. There is a risk of information overlap in the disentangling process which results in less speech naturalness. To overcome such limits, we propose a two-stage model to disentangle speech representations in a self-supervised mann","authors_text":"Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang, Yong Zhang, Ziqi Liang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-30T02:23:37Z","title":"EAD-VC: Enhancing Speech Auto-Disentanglement for Voice Conversion with IFUB Estimator and Joint Text-Guided Consistent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19212","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:c30f20fc142c0763dde272ccbb6a434a481f9b63010bc674dba2def12311fd2b","target":"record","created_at":"2026-07-05T08:13:40Z","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":"60a9b8bd9d6126d951a4e47e0feb633977db0d2e6a271e7ba62cb189cc3a2b67","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-30T02:23:37Z","title_canon_sha256":"27cd83350ecbe7152483507fce0418ffbbc1303b5eb47cef890c3acc115d956d"},"schema_version":"1.0","source":{"id":"2404.19212","kind":"arxiv","version":1}},"canonical_sha256":"cfe00696b5eb352f98779a083623ad31a61c0d06745e9471c74252c34b8931c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfe00696b5eb352f98779a083623ad31a61c0d06745e9471c74252c34b8931c7","first_computed_at":"2026-07-05T08:13:40.022477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:40.022477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1ttvGNPuLSlyaWVxOHpS88rOg88kWDMyEMcVIqoVdvm1lY2ymS1JHG3RkKHEwov7UPBJzql9veqqedzL+wwzDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:40.023060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c30f20fc142c0763dde272ccbb6a434a481f9b63010bc674dba2def12311fd2b","sha256:516df287dba8c9c21e89d44f161c0959231f58c15486ce03b33b400a20ed13b3"],"state_sha256":"8dc97b59533c734f5a45b2ce50b6469550e47661db984c11bb87abfb8b382a10"}