{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BDLQ7RY63IOFXWES3XBKO3SI3F","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":"34ecf3621aa01057bb177f9f3568450b57939638fcb1a7e423c8533f13415feb","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-03T11:15:16Z","title_canon_sha256":"54fc39d2fe8be5f4d91c11b650cb3a245cf2ef4a0ff961057af1568499fb72a3"},"schema_version":"1.0","source":{"id":"2406.01205","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01205","created_at":"2026-07-05T11:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01205v3","created_at":"2026-07-05T11:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01205","created_at":"2026-07-05T11:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"BDLQ7RY63IOF","created_at":"2026-07-05T11:15:37Z"},{"alias_kind":"pith_short_16","alias_value":"BDLQ7RY63IOFXWES","created_at":"2026-07-05T11:15:37Z"},{"alias_kind":"pith_short_8","alias_value":"BDLQ7RY6","created_at":"2026-07-05T11:15:37Z"}],"graph_snapshots":[{"event_id":"sha256:c5a0d854cf0224adba74be39595f3f0f6734f3cef268f1dc8d810a1dacc1ca39","target":"graph","created_at":"2026-07-05T11:15:37Z","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/2406.01205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style. Prior zero-shot TTS models only mimic the speaker's voice without further control and adjustment capabilities while prior controllable TTS models cannot perform speaker-specific voice generation. Therefore, ControlSpeech focuses on a more challenging task: a TTS system with controllable timbre, content, and style at the same time. ControlSpeech takes speech prompts, content prompts, and style prompts as inputs and u","authors_text":"Hai Huang, Jialong Zuo, Minghui Fang, Qian Chen, Shengpeng Ji, Siqi Zheng, Wen Wang, Xize Cheng, Zehan Wang, Zhou Zhao, Ziyue Jiang","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-03T11:15:16Z","title":"ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01205","kind":"arxiv","version":3},"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":"sha256:2ee4967919c3281b1736e76ce9a3448a155c5b3c7fec06831f637919e1a2bfd9","target":"record","created_at":"2026-07-05T11:15:37Z","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":"34ecf3621aa01057bb177f9f3568450b57939638fcb1a7e423c8533f13415feb","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-03T11:15:16Z","title_canon_sha256":"54fc39d2fe8be5f4d91c11b650cb3a245cf2ef4a0ff961057af1568499fb72a3"},"schema_version":"1.0","source":{"id":"2406.01205","kind":"arxiv","version":3}},"canonical_sha256":"08d70fc71eda1c5bd892ddc2a76e48d95e80b0450e6593ef3166616fbd3bcc12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08d70fc71eda1c5bd892ddc2a76e48d95e80b0450e6593ef3166616fbd3bcc12","first_computed_at":"2026-07-05T11:15:37.661688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:37.661688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JpZHJMHQnuvYT0NyAUyrZnc0USf5MDeyp74PazdtoQq+m1A5ILipB5Ma8kEjJSnDNuYo72odp67stCobzMOYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:37.662230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01205","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ee4967919c3281b1736e76ce9a3448a155c5b3c7fec06831f637919e1a2bfd9","sha256:c5a0d854cf0224adba74be39595f3f0f6734f3cef268f1dc8d810a1dacc1ca39"],"state_sha256":"81896283deaaff50e583c27160a6c8fae71d0cb14c5593d4735dc086f0e42381"}