{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FQM4XTKBOK7262WZCVSLHRV6HE","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":"0cd07dc72e5bfd507678c6690246cda449e601ad9923212051779f68c63806f2","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T07:06:46Z","title_canon_sha256":"d4603213222801d02497bdb2f3ac23b7e3b3ca514272c6114df965fbb4b4ab29"},"schema_version":"1.0","source":{"id":"2509.02020","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02020","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02020v2","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02020","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"FQM4XTKBOK72","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"FQM4XTKBOK7262WZ","created_at":"2026-07-05T12:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"FQM4XTKB","created_at":"2026-07-05T12:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:36247bb83ea86306e72b340641978af4dfff4579807270866cfc075d69ecc283","target":"graph","created_at":"2026-07-05T12:04:40Z","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/2509.02020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current dialogue generation approaches typically require the complete dialogue text before synthesis and produce a single, inseparable speech containing all voices, making them unsuitable for interactive chat; moreover, they suffer from unstable synthesis, inaccurate speaker transitions, and incoherent prosody. In this work, we present FireRedTTS-2, a long-form streaming TTS system for multi-speaker dialogue generation, delivering stable, natural speech with reliable speaker switching and context-aware prosody. A new 12.5Hz streaming speech tokenizer accelerates training and inference, extends","authors_text":"Feiyu Shen, Fenglong Xie, Junjie Li, Kun Xie, Xu Tang, Yao Hu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T07:06:46Z","title":"FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02020","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:e30f9530fea71634fb86d132ce63a139d7cbef54735871d5e703e8de70f6b11f","target":"record","created_at":"2026-07-05T12:04:40Z","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":"0cd07dc72e5bfd507678c6690246cda449e601ad9923212051779f68c63806f2","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T07:06:46Z","title_canon_sha256":"d4603213222801d02497bdb2f3ac23b7e3b3ca514272c6114df965fbb4b4ab29"},"schema_version":"1.0","source":{"id":"2509.02020","kind":"arxiv","version":2}},"canonical_sha256":"2c19cbcd4172bfaf6ad91564b3c6be392ff6e8655ab95892d413ed07fca70c56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c19cbcd4172bfaf6ad91564b3c6be392ff6e8655ab95892d413ed07fca70c56","first_computed_at":"2026-07-05T12:04:40.889976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:40.889976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jn37bmsryYg7my1yJ9CGQJOrTNb512GlnIkUfh/gdYc2pyf2FlqNCg8IQgs6GLPhINhOEUGcpQYr4VPMCww9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:40.890460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02020","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e30f9530fea71634fb86d132ce63a139d7cbef54735871d5e703e8de70f6b11f","sha256:36247bb83ea86306e72b340641978af4dfff4579807270866cfc075d69ecc283"],"state_sha256":"64d9389f34e2ec6d4ede2b8fb2cd0db6a38a846d364d5722669ec9a86c1d1e93"}