{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P3DLO5HCEMXBR5C6WWMP2XTHXI","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":"d6d6594e9278a6d6758c636b02041a06c56048ff2cac5a8d91f41183c925a42b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-06T16:51:04Z","title_canon_sha256":"22861316a64ac63b12cfba4962dee1b2abc760d09edd55a54717116b7f5e951a"},"schema_version":"1.0","source":{"id":"2601.03170","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.03170","created_at":"2026-05-20T00:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2601.03170v2","created_at":"2026-05-20T00:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03170","created_at":"2026-05-20T00:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"P3DLO5HCEMXB","created_at":"2026-05-20T00:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"P3DLO5HCEMXBR5C6","created_at":"2026-05-20T00:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"P3DLO5HC","created_at":"2026-05-20T00:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:0643cef0f034e813e69b30e689bdaf1d35c35d7b48f72ba1b82986aace87f7a5","target":"graph","created_at":"2026-05-20T00:04:20Z","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/2601.03170/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public datasets or complex multi-stage training. In this paper, we propose TED-TTS, a training-free controllable framework for pretrained zero-shot TTS to enable intra-utterance emotion and duration expression. Specifically, we propose a segment-aware emotion conditioning strategy that combines causal masking with monotonic stream alignment filtering to isolate emotio","authors_text":"Junchuan Zhao, Nan Lu, Qifan Liang, Ruixin Wei, Ye Wang, Yuansen Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-06T16:51:04Z","title":"TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.03170","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:dd2a9f02a01a1da8ddd8cd95762775cbb8b89498ea8e4dfa75907eba0bfb0de2","target":"record","created_at":"2026-05-20T00:04:20Z","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":"d6d6594e9278a6d6758c636b02041a06c56048ff2cac5a8d91f41183c925a42b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-06T16:51:04Z","title_canon_sha256":"22861316a64ac63b12cfba4962dee1b2abc760d09edd55a54717116b7f5e951a"},"schema_version":"1.0","source":{"id":"2601.03170","kind":"arxiv","version":2}},"canonical_sha256":"7ec6b774e2232e18f45eb598fd5e67ba360a9ad0c71a4a9f6aa80f993def5a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec6b774e2232e18f45eb598fd5e67ba360a9ad0c71a4a9f6aa80f993def5a0d","first_computed_at":"2026-05-20T00:04:20.427573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:20.427573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IH1dnOPgex+JoxQ5gcF3ZfQh1XN/c315xy8xGs2yPNXuQ8uWaiDgUBFL2BFzn8EWNtPINJOlWdKGHzXofY1WBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:20.428432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.03170","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd2a9f02a01a1da8ddd8cd95762775cbb8b89498ea8e4dfa75907eba0bfb0de2","sha256:0643cef0f034e813e69b30e689bdaf1d35c35d7b48f72ba1b82986aace87f7a5"],"state_sha256":"c7951f4f083a45b68ec4b3cad62cb8a5a996680a4f3210ae58b5ff55cac760d5"}