{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NFRTCUAEF4MWQ6RYGEQOH4TKTB","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":"8a6db8f31c23d80ba207247233f8ca857944ea611084188c401f3fa7fee7c532","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T07:46:16Z","title_canon_sha256":"37701e29dd686085e4afa820db58ca3e41d5c1a46ae00afa23edd84a1b58b3d6"},"schema_version":"1.0","source":{"id":"2606.00066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00066","created_at":"2026-06-02T00:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00066v1","created_at":"2026-06-02T00:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00066","created_at":"2026-06-02T00:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"NFRTCUAEF4MW","created_at":"2026-06-02T00:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"NFRTCUAEF4MWQ6RY","created_at":"2026-06-02T00:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"NFRTCUAE","created_at":"2026-06-02T00:03:13Z"}],"graph_snapshots":[{"event_id":"sha256:6559d5cabbbbf67b2e7ea1de165f49fce6894e0439783e65f735766b3ce9d20f","target":"graph","created_at":"2026-06-02T00:03:13Z","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/2606.00066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker identity. We discover that emotion embedding emerges as a linearly decodable direction of frozen hidden states, nearly orthogonal to the direction embedding speaker identity. This inspires a plug-and-play framework DUET for emotion control over pretrained diffusion and flow-matching based TTS models. During generation, DUET unifies dual-space control to achieve fine-grained emotion intervention in a single per-step update","authors_text":"Longbing Cao, Xu Zhang, Zhangkai Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T07:46:16Z","title":"DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00066","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:c106d1dc88eb9783feb5c90cb859c1af3ac3d7e976febf8b8207cc3cc3283403","target":"record","created_at":"2026-06-02T00:03:13Z","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":"8a6db8f31c23d80ba207247233f8ca857944ea611084188c401f3fa7fee7c532","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T07:46:16Z","title_canon_sha256":"37701e29dd686085e4afa820db58ca3e41d5c1a46ae00afa23edd84a1b58b3d6"},"schema_version":"1.0","source":{"id":"2606.00066","kind":"arxiv","version":1}},"canonical_sha256":"69633150042f19687a383120e3f26a986f8c6e22e0eb955b51bc4a14c86c8ef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69633150042f19687a383120e3f26a986f8c6e22e0eb955b51bc4a14c86c8ef3","first_computed_at":"2026-06-02T00:03:13.915761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T00:03:13.915761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uWt/18q19OcdJew0ZVRYMlx/BofeIKUML2zBbI7zziYnVFtAtIWxJIfnLC7+2P07fwN7AAk6KFrDb8yKRjkpCQ==","signature_status":"signed_v1","signed_at":"2026-06-02T00:03:13.916302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c106d1dc88eb9783feb5c90cb859c1af3ac3d7e976febf8b8207cc3cc3283403","sha256:6559d5cabbbbf67b2e7ea1de165f49fce6894e0439783e65f735766b3ce9d20f"],"state_sha256":"eadee25a4cc9c68a926950b14de67c61ff66a06145352cfdc4c886f041d028aa"}