{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CWTVEGEJ5LXUUQN2UBBWLDZRYD","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":"615fe8d62be534b0281a49027e6b3683faff6b74f5cb12d3b75151b8f206dc67","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-02T04:17:42Z","title_canon_sha256":"d1f3e4470f8c792bf4578b9511893eeb9f435fff3348dff1c53647a883aab496"},"schema_version":"1.0","source":{"id":"2412.01100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01100","created_at":"2026-07-05T10:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01100v2","created_at":"2026-07-05T10:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01100","created_at":"2026-07-05T10:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"CWTVEGEJ5LXU","created_at":"2026-07-05T10:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"CWTVEGEJ5LXUUQN2","created_at":"2026-07-05T10:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"CWTVEGEJ","created_at":"2026-07-05T10:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:56f1b4a569f3d5f8501e935ff3e4c8494be3d73287e64c8984a5d1cf14d6c0fe","target":"graph","created_at":"2026-07-05T10:09:12Z","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/2412.01100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes the zero-shot spontaneous style TTS system for the ISCSLP 2024 Conversational Voice Clone Challenge (CoVoC). We propose a LLaMA-based codec language model with a delay pattern to achieve spontaneous style voice cloning. To improve speech intelligibility, we introduce the Classifier-Free Guidance (CFG) strategy in the language model to strengthen conditional guidance on token prediction. To generate high-quality utterances, we adopt effective data preprocessing operations and fine-tune our model with selected high-quality spontaneous speech data. The official evaluations in","authors_text":"Jun Chen, Runchuan Ye, Shun Lei, Shuoyi Zhou, Weihao Wu, Weiqin Li, Yixuan Zhou, Zhiyong Wu, Zijian Lin","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-02T04:17:42Z","title":"The Codec Language Model-based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01100","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:b30a62749e2ad390b3b0933e45ec7ec992fdec9160e33f131e4bec9032fbf1cc","target":"record","created_at":"2026-07-05T10:09:12Z","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":"615fe8d62be534b0281a49027e6b3683faff6b74f5cb12d3b75151b8f206dc67","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-02T04:17:42Z","title_canon_sha256":"d1f3e4470f8c792bf4578b9511893eeb9f435fff3348dff1c53647a883aab496"},"schema_version":"1.0","source":{"id":"2412.01100","kind":"arxiv","version":2}},"canonical_sha256":"15a7521889eaef4a41baa043658f31c0ea2c1032de51c015145a00122ff8a7e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15a7521889eaef4a41baa043658f31c0ea2c1032de51c015145a00122ff8a7e4","first_computed_at":"2026-07-05T10:09:12.606611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:12.606611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8gsOItRyGdOEZEFwjF/YKX5xl6ic9rfVO3aqbTWo0bKBlkZav2pOv2nccqsTPyq3zzeUv3kdn64htiRbap+rAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:12.607069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b30a62749e2ad390b3b0933e45ec7ec992fdec9160e33f131e4bec9032fbf1cc","sha256:56f1b4a569f3d5f8501e935ff3e4c8494be3d73287e64c8984a5d1cf14d6c0fe"],"state_sha256":"ffaee8cb3d05af2f1be29dda3140bcc13ee11510d2a75579ba7f40b0ab140cbc"}