{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P643TLW4VA33DM3AGNKSNXLSRP","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":"047401baf55553bae7feb44b4c516ff5913a4a5eb04447c73dfdff4ac9fce6c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T04:43:17Z","title_canon_sha256":"06011b31dd0aa45ea9f1874d223b523681b9a7ccf941291a6bd6666f9241d83a"},"schema_version":"1.0","source":{"id":"2505.18972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18972","created_at":"2026-07-05T11:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18972v1","created_at":"2026-07-05T11:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18972","created_at":"2026-07-05T11:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"P643TLW4VA33","created_at":"2026-07-05T11:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"P643TLW4VA33DM3A","created_at":"2026-07-05T11:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"P643TLW4","created_at":"2026-07-05T11:09:22Z"}],"graph_snapshots":[{"event_id":"sha256:12c6027915ff21912e25e48427d79daa329a45ea171b6839fd0d72e3ca77d6f1","target":"graph","created_at":"2026-07-05T11:09:22Z","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/2505.18972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores multi-modal controllable Text-to-Speech Synthesis (TTS) where the voice can be generated from face image, and the characteristics of output speech (e.g., pace, noise level, distance, tone, place) can be controllable with natural text description. Specifically, we aim to mitigate the following three challenges in face-driven TTS systems. 1) To overcome the limited audio quality of audio-visual speech corpora, we propose a training method that additionally utilizes high-quality audio-only speech corpora. 2) To generate voices not only from real human faces but also from artis","authors_text":"Honglie Chen, Maja Pantic, Minsu Kim, Pingchuan Ma, Stavros Petridis","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T04:43:17Z","title":"Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18972","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:a4eaf5f8f480ea59b72a5c9f2af9cfb86444a349f258ee19a468b5b0dbf43915","target":"record","created_at":"2026-07-05T11:09:22Z","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":"047401baf55553bae7feb44b4c516ff5913a4a5eb04447c73dfdff4ac9fce6c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-25T04:43:17Z","title_canon_sha256":"06011b31dd0aa45ea9f1874d223b523681b9a7ccf941291a6bd6666f9241d83a"},"schema_version":"1.0","source":{"id":"2505.18972","kind":"arxiv","version":1}},"canonical_sha256":"7fb9b9aedca837b1b360335526dd728befcf7a40441fdde42a79e88688c22287","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fb9b9aedca837b1b360335526dd728befcf7a40441fdde42a79e88688c22287","first_computed_at":"2026-07-05T11:09:22.726811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:22.726811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BdVRfY0r7tqo0j/aJOV/TBUm/xifp9hq09UDUiyJVtH4x44pFexIxyUmkemyz6jwCRyubYhobv1+r74XTfG2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:22.727340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4eaf5f8f480ea59b72a5c9f2af9cfb86444a349f258ee19a468b5b0dbf43915","sha256:12c6027915ff21912e25e48427d79daa329a45ea171b6839fd0d72e3ca77d6f1"],"state_sha256":"7df80b78baf226f37baa7ba1b84e225a6195e934540b47f9d8a50dcd8e43ac9d"}