{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NWKEF2DD5CLI2CJZJT4RY7CI4T","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":"011fe1aa18441c1dbd4b56fd46694a3d24ed138e22dc32de4e0b0d99cf9833df","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-26T02:23:42Z","title_canon_sha256":"a2238818fad2890adc76dcc21454ee6a26fef63866a23a1b16bf3a610805b612"},"schema_version":"1.0","source":{"id":"2506.20945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20945","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20945v1","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20945","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_12","alias_value":"NWKEF2DD5CLI","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"NWKEF2DD5CLI2CJZ","created_at":"2026-07-05T11:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"NWKEF2DD","created_at":"2026-07-05T11:27:36Z"}],"graph_snapshots":[{"event_id":"sha256:9c48d93817d5e4c82ff59627fb86a2fe1200d9ed7db27b0ee500cc7bd56d6e69","target":"graph","created_at":"2026-07-05T11:27:36Z","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/2506.20945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controllable speech synthesis aims to control the style of generated speech using reference input, which can be of various modalities. Existing face-based methods struggle with robustness and generalization due to data quality constraints, while text prompt methods offer limited diversity and fine-grained control. Although multimodal approaches aim to integrate various modalities, their reliance on fully matched training data significantly constrains their performance and applicability. This paper proposes a 3-stage multimodal controllable speech synthesis framework to address these challenges","authors_text":"Jie Chen, Long Ma, Rui Niu, Weihao Wu, Zhiyong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-26T02:23:42Z","title":"A Multi-Stage Framework for Multimodal Controllable Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20945","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":"sha256:139cf543c1acb44ee7fcb40986212e25fcc45860ed9d70344320c5106aadf8d6","target":"record","created_at":"2026-07-05T11:27:36Z","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":"011fe1aa18441c1dbd4b56fd46694a3d24ed138e22dc32de4e0b0d99cf9833df","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-26T02:23:42Z","title_canon_sha256":"a2238818fad2890adc76dcc21454ee6a26fef63866a23a1b16bf3a610805b612"},"schema_version":"1.0","source":{"id":"2506.20945","kind":"arxiv","version":1}},"canonical_sha256":"6d9442e863e8968d09394cf91c7c48e4cc7fd7e68208d74cb459967f84c2c9e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d9442e863e8968d09394cf91c7c48e4cc7fd7e68208d74cb459967f84c2c9e1","first_computed_at":"2026-07-05T11:27:36.468902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:36.468902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b5l35tero/qH+x6F9KzQWqk7TS3ngQwmBAxYVBBCTYvg6+5gDXYNk37HZclLnUwyh3qWz5l6mWswEvtmMrf/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:36.469362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:139cf543c1acb44ee7fcb40986212e25fcc45860ed9d70344320c5106aadf8d6","sha256:9c48d93817d5e4c82ff59627fb86a2fe1200d9ed7db27b0ee500cc7bd56d6e69"],"state_sha256":"dd1b06a5507394fd43b5a0e303bb97445cf4571b6fa2180f1843b32fd4cb2b2d"}