{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZXC6SZJPR4Q2ITZOT5CCSPSFBG","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":"5642db96c8afc7dfd51cf5e24a86eeee0b35c7917bd7895c75e5bf1563eb300b","cross_cats_sorted":["cs.HC","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-08T23:17:09Z","title_canon_sha256":"1b80c716731f9b6e11d127125215e4df6b58d1d8821ee191f52d3dfdbc88ae9e"},"schema_version":"1.0","source":{"id":"2608.08362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08362","created_at":"2026-08-11T01:22:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08362v1","created_at":"2026-08-11T01:22:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08362","created_at":"2026-08-11T01:22:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZXC6SZJPR4Q2","created_at":"2026-08-11T01:22:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZXC6SZJPR4Q2ITZO","created_at":"2026-08-11T01:22:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZXC6SZJP","created_at":"2026-08-11T01:22:25Z"}],"graph_snapshots":[{"event_id":"sha256:bf249dc5996c2ee2af626f87ceef2360a05f51b54211d46c3827f8602bfe4899","target":"graph","created_at":"2026-08-11T01:22:25Z","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/2608.08362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Text-To-Speech (TTS) systems have achieved strong naturalness and zero-shot voice cloning performance, but fine-grained control of expressive speech at the word or phoneme level remains challenging. We propose CtrlSpeech, a controllable, expressive TTS framework with coarse-to-fine control. Built on the DiTAR architecture, CtrlSpeech combines global speaker conditioning with phone-aligned pitch, loudness, and duration signals, enabling localized prosodic control while preserving the target speaker's timbre. This design allows users to adjust expressive attributes at a fine temporal gran","authors_text":"Caren Chen, David Harwath, Gerard Medioni, Manoj Aggarwal, Rohith Kumar, Xiaohang Sun, Zhisheng Zheng, Zhu Liu","cross_cats":["cs.HC","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-08T23:17:09Z","title":"CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08362","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:e60c113e27b222738b3f5cc6ccac83283582c3cbdc86501ae4f4e72ddb04d87b","target":"record","created_at":"2026-08-11T01:22:25Z","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":"5642db96c8afc7dfd51cf5e24a86eeee0b35c7917bd7895c75e5bf1563eb300b","cross_cats_sorted":["cs.HC","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-08T23:17:09Z","title_canon_sha256":"1b80c716731f9b6e11d127125215e4df6b58d1d8821ee191f52d3dfdbc88ae9e"},"schema_version":"1.0","source":{"id":"2608.08362","kind":"arxiv","version":1}},"canonical_sha256":"cdc5e9652f8f21a44f2e9f44293e4509aa57445b3b733ae9ca1dcd082124d36a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdc5e9652f8f21a44f2e9f44293e4509aa57445b3b733ae9ca1dcd082124d36a","first_computed_at":"2026-08-11T01:22:25.430170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:22:25.430170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EzGl0FoRzzEKNr9HJ9qWK07d+VGHDlbgCgYSp80fZZ7WajB1XCTviKYaZ4hR9US6hgbtXdBH9AnxzNtwwGIlAw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:22:25.432609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e60c113e27b222738b3f5cc6ccac83283582c3cbdc86501ae4f4e72ddb04d87b","sha256:bf249dc5996c2ee2af626f87ceef2360a05f51b54211d46c3827f8602bfe4899"],"state_sha256":"cb2c01f1036b1a7ccbee14541e76684ef7724c8db7f3fc7bf705250e20f9c36a"}