{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5WGDOVNIZDOECB2VB5KSDH7PPM","short_pith_number":"pith:5WGDOVNI","schema_version":"1.0","canonical_sha256":"ed8c3755a8c8dc4107550f55219fef7b34eb1e844867e46d29b959c7e4f36817","source":{"kind":"arxiv","id":"2503.14345","version":2},"attestation_state":"computed","paper":{"title":"MoonCast: High-Quality Zero-Shot Podcast Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongchao Yang, Jianwei Yu, Kai Shen, Tao Qin, Xiangyang Li, Xinyu Zhou, Xu Tan, Yichong Leng, Zeqian Ju, Zhengtao Wang","submitted_at":"2025-03-18T15:25:08Z","abstract_excerpt":"Recent advances in text-to-speech synthesis have achieved notable success in generating high-quality short utterances for individual speakers. However, these systems still face challenges when extending their capabilities to long, multi-speaker, and spontaneous dialogues, typical of real-world scenarios such as podcasts. These limitations arise from two primary challenges: 1) long speech: podcasts typically span several minutes, exceeding the upper limit of most existing work; 2) spontaneity: podcasts are marked by their spontaneous, oral nature, which sharply contrasts with formal, written co"},"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":"2503.14345","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-03-18T15:25:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"f387a97f27b4eae6ed9c64ef69c159d11491b13f4b264c219640106fe0c58f4c","abstract_canon_sha256":"528a40b50c6577b0742b61795b2ccc6eb5700202e2e1a97200bf2743bebc39c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:18.851806Z","signature_b64":"39B3MPZhmQpSL+uNTCloFffsPnM/IKxeLm2fwBF24sax3Y2JvrOvEFoHQZZS94HNEJPlPy8oHGGX551c2wa3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed8c3755a8c8dc4107550f55219fef7b34eb1e844867e46d29b959c7e4f36817","last_reissued_at":"2026-07-05T10:34:18.850891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:18.850891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoonCast: High-Quality Zero-Shot Podcast Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongchao Yang, Jianwei Yu, Kai Shen, Tao Qin, Xiangyang Li, Xinyu Zhou, Xu Tan, Yichong Leng, Zeqian Ju, Zhengtao Wang","submitted_at":"2025-03-18T15:25:08Z","abstract_excerpt":"Recent advances in text-to-speech synthesis have achieved notable success in generating high-quality short utterances for individual speakers. However, these systems still face challenges when extending their capabilities to long, multi-speaker, and spontaneous dialogues, typical of real-world scenarios such as podcasts. These limitations arise from two primary challenges: 1) long speech: podcasts typically span several minutes, exceeding the upper limit of most existing work; 2) spontaneity: podcasts are marked by their spontaneous, oral nature, which sharply contrasts with formal, written co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14345","kind":"arxiv","version":2},"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/2503.14345/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":"2503.14345","created_at":"2026-07-05T10:34:18.851008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14345v2","created_at":"2026-07-05T10:34:18.851008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14345","created_at":"2026-07-05T10:34:18.851008+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WGDOVNIZDOE","created_at":"2026-07-05T10:34:18.851008+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WGDOVNIZDOECB2V","created_at":"2026-07-05T10:34:18.851008+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WGDOVNI","created_at":"2026-07-05T10:34:18.851008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19325","citing_title":"Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30993","citing_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09318","citing_title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08709","citing_title":"Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM","json":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM.json","graph_json":"https://pith.science/api/pith-number/5WGDOVNIZDOECB2VB5KSDH7PPM/graph.json","events_json":"https://pith.science/api/pith-number/5WGDOVNIZDOECB2VB5KSDH7PPM/events.json","paper":"https://pith.science/paper/5WGDOVNI"},"agent_actions":{"view_html":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM","download_json":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM.json","view_paper":"https://pith.science/paper/5WGDOVNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14345&json=true","fetch_graph":"https://pith.science/api/pith-number/5WGDOVNIZDOECB2VB5KSDH7PPM/graph.json","fetch_events":"https://pith.science/api/pith-number/5WGDOVNIZDOECB2VB5KSDH7PPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM/action/storage_attestation","attest_author":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM/action/author_attestation","sign_citation":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM/action/citation_signature","submit_replication":"https://pith.science/pith/5WGDOVNIZDOECB2VB5KSDH7PPM/action/replication_record"}},"created_at":"2026-07-05T10:34:18.851008+00:00","updated_at":"2026-07-05T10:34:18.851008+00:00"}