{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NFRTCUAEF4MWQ6RYGEQOH4TKTB","short_pith_number":"pith:NFRTCUAE","schema_version":"1.0","canonical_sha256":"69633150042f19687a383120e3f26a986f8c6e22e0eb955b51bc4a14c86c8ef3","source":{"kind":"arxiv","id":"2606.00066","version":1},"attestation_state":"computed","paper":{"title":"DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Longbing Cao, Xu Zhang, Zhangkai Wu","submitted_at":"2026-05-20T07:46:16Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.00066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-20T07:46:16Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"37701e29dd686085e4afa820db58ca3e41d5c1a46ae00afa23edd84a1b58b3d6","abstract_canon_sha256":"8a6db8f31c23d80ba207247233f8ca857944ea611084188c401f3fa7fee7c532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T00:03:13.916302Z","signature_b64":"uWt/18q19OcdJew0ZVRYMlx/BofeIKUML2zBbI7zziYnVFtAtIWxJIfnLC7+2P07fwN7AAk6KFrDb8yKRjkpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69633150042f19687a383120e3f26a986f8c6e22e0eb955b51bc4a14c86c8ef3","last_reissued_at":"2026-06-02T00:03:13.915761Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T00:03:13.915761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Longbing Cao, Xu Zhang, Zhangkai Wu","submitted_at":"2026-05-20T07:46:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00066","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.00066/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.00066","created_at":"2026-06-02T00:03:13.915841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00066v1","created_at":"2026-06-02T00:03:13.915841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00066","created_at":"2026-06-02T00:03:13.915841+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFRTCUAEF4MW","created_at":"2026-06-02T00:03:13.915841+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFRTCUAEF4MWQ6RY","created_at":"2026-06-02T00:03:13.915841+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFRTCUAE","created_at":"2026-06-02T00:03:13.915841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB","json":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB.json","graph_json":"https://pith.science/api/pith-number/NFRTCUAEF4MWQ6RYGEQOH4TKTB/graph.json","events_json":"https://pith.science/api/pith-number/NFRTCUAEF4MWQ6RYGEQOH4TKTB/events.json","paper":"https://pith.science/paper/NFRTCUAE"},"agent_actions":{"view_html":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB","download_json":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB.json","view_paper":"https://pith.science/paper/NFRTCUAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00066&json=true","fetch_graph":"https://pith.science/api/pith-number/NFRTCUAEF4MWQ6RYGEQOH4TKTB/graph.json","fetch_events":"https://pith.science/api/pith-number/NFRTCUAEF4MWQ6RYGEQOH4TKTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB/action/storage_attestation","attest_author":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB/action/author_attestation","sign_citation":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB/action/citation_signature","submit_replication":"https://pith.science/pith/NFRTCUAEF4MWQ6RYGEQOH4TKTB/action/replication_record"}},"created_at":"2026-06-02T00:03:13.915841+00:00","updated_at":"2026-06-02T00:03:13.915841+00:00"}