{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DIMANKXSJJK3LGI3WMBAB5MRGS","short_pith_number":"pith:DIMANKXS","schema_version":"1.0","canonical_sha256":"1a1806aaf24a55b5991bb30200f591349047b270e0bbd4dfd70bdf29fc2f4a17","source":{"kind":"arxiv","id":"2606.21933","version":1},"attestation_state":"computed","paper":{"title":"ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bei Liu, Bin Long, Boyi Kang, Jiahao Pan, Junlan Feng, Liumeng Xue, Ruosong Yang, Shilei Zhang, Sitong Cheng, Wei Xue, Weizhen Bian, Yue Wang","submitted_at":"2026-06-20T08:00:12Z","abstract_excerpt":"Recent advances in text-to-speech (TTS) have greatly improved speech naturalness, speaker similarity, and controllability. However, most existing controllable TTS systems still rely on explicit user-provided style prompts, making it difficult to automatically determine how a sentence should be spoken in long and complex conversational scenarios. This proposal introduces the ISCSLP 2026 CoT-TTS Challenge, which aims to evaluate whether a system can infer the intended speaking manner from contextual information and generate speech consistent with both the reasoning output and the surrounding sce"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.21933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-20T08:00:12Z","cross_cats_sorted":[],"title_canon_sha256":"fad739fda7cb885181bdc3822470c779e96e2fb1c7f9bc9d6b35f2b04afd8cbe","abstract_canon_sha256":"d47b8cade249ac57337d009602d3e33bc2618c50088e1f7e8162f2713395c4a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:03.287438Z","signature_b64":"jziBINsBZrWAGwwOBqcB4eEnkhDOYhxwP//Xi3DVu5PFKu8xRTd31/djZUy6m9YJoHAI7oFHXNeKzLWUApBcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a1806aaf24a55b5991bb30200f591349047b270e0bbd4dfd70bdf29fc2f4a17","last_reissued_at":"2026-06-23T02:13:03.286983Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:03.286983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bei Liu, Bin Long, Boyi Kang, Jiahao Pan, Junlan Feng, Liumeng Xue, Ruosong Yang, Shilei Zhang, Sitong Cheng, Wei Xue, Weizhen Bian, Yue Wang","submitted_at":"2026-06-20T08:00:12Z","abstract_excerpt":"Recent advances in text-to-speech (TTS) have greatly improved speech naturalness, speaker similarity, and controllability. However, most existing controllable TTS systems still rely on explicit user-provided style prompts, making it difficult to automatically determine how a sentence should be spoken in long and complex conversational scenarios. This proposal introduces the ISCSLP 2026 CoT-TTS Challenge, which aims to evaluate whether a system can infer the intended speaking manner from contextual information and generate speech consistent with both the reasoning output and the surrounding sce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21933","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.21933/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.21933","created_at":"2026-06-23T02:13:03.287051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21933v1","created_at":"2026-06-23T02:13:03.287051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21933","created_at":"2026-06-23T02:13:03.287051+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIMANKXSJJK3","created_at":"2026-06-23T02:13:03.287051+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIMANKXSJJK3LGI3","created_at":"2026-06-23T02:13:03.287051+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIMANKXS","created_at":"2026-06-23T02:13:03.287051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS","json":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS.json","graph_json":"https://pith.science/api/pith-number/DIMANKXSJJK3LGI3WMBAB5MRGS/graph.json","events_json":"https://pith.science/api/pith-number/DIMANKXSJJK3LGI3WMBAB5MRGS/events.json","paper":"https://pith.science/paper/DIMANKXS"},"agent_actions":{"view_html":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS","download_json":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS.json","view_paper":"https://pith.science/paper/DIMANKXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21933&json=true","fetch_graph":"https://pith.science/api/pith-number/DIMANKXSJJK3LGI3WMBAB5MRGS/graph.json","fetch_events":"https://pith.science/api/pith-number/DIMANKXSJJK3LGI3WMBAB5MRGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS/action/storage_attestation","attest_author":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS/action/author_attestation","sign_citation":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS/action/citation_signature","submit_replication":"https://pith.science/pith/DIMANKXSJJK3LGI3WMBAB5MRGS/action/replication_record"}},"created_at":"2026-06-23T02:13:03.287051+00:00","updated_at":"2026-06-23T02:13:03.287051+00:00"}