{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XMXLN3AW5GPDERU46DJGKUU3TW","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":"3c9ca8cdff5d88d0439271f62c07df3fe61375b79c02e863b8e2dc3f9b41bbcb","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-05T06:48:02Z","title_canon_sha256":"5e01eda909f4e14a78cf555436330df01af86d472b9670aab6d4f608ca9f1651"},"schema_version":"1.0","source":{"id":"2409.03283","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03283","created_at":"2026-07-05T10:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03283v2","created_at":"2026-07-05T10:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03283","created_at":"2026-07-05T10:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"XMXLN3AW5GPD","created_at":"2026-07-05T10:47:30Z"},{"alias_kind":"pith_short_16","alias_value":"XMXLN3AW5GPDERU4","created_at":"2026-07-05T10:47:30Z"},{"alias_kind":"pith_short_8","alias_value":"XMXLN3AW","created_at":"2026-07-05T10:47:30Z"}],"graph_snapshots":[{"event_id":"sha256:f3946a08bffb8009f97cb0581f1343aef5853710f089a8a34ecfbcc8455907d5","target":"graph","created_at":"2026-07-05T10:47:30Z","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/2409.03283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work proposes FireRedTTS, a foundation text-to-speech framework, to meet the growing demands for personalized and diverse generative speech applications. The framework comprises three parts: data processing, foundation system, and downstream applications. First, we comprehensively present our data processing pipeline, which transforms massive raw audio into a large-scale high-quality TTS dataset with rich annotations and a wide coverage of content, speaking style, and timbre. Then, we propose a language-model-based foundation TTS system. The speech signal is compressed into discrete seman","authors_text":"Fei-Yu Shen, Feng-Long Xie, Hao-Han Guo, Kai-Tuo Xu, Kun Liu, Kun Xie, Xu Tang, Yao Hu, Yi-Chen Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-05T06:48:02Z","title":"FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03283","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":"sha256:0fc0a4b74ea75f6dd281d893aa6f4d18429dce13db2c32e6731f38cb8b3f955c","target":"record","created_at":"2026-07-05T10:47:30Z","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":"3c9ca8cdff5d88d0439271f62c07df3fe61375b79c02e863b8e2dc3f9b41bbcb","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-05T06:48:02Z","title_canon_sha256":"5e01eda909f4e14a78cf555436330df01af86d472b9670aab6d4f608ca9f1651"},"schema_version":"1.0","source":{"id":"2409.03283","kind":"arxiv","version":2}},"canonical_sha256":"bb2eb6ec16e99e32469cf0d265529b9db874d824f61db5a1f7352808ad439b6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb2eb6ec16e99e32469cf0d265529b9db874d824f61db5a1f7352808ad439b6c","first_computed_at":"2026-07-05T10:47:30.748793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:30.748793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wKUAmn+NbGa0+geyIWAuZ8bbSPs5fQyAf34HerMXy5s8zSO1ypZlVusxUtytkcsHUjV3u1djegFFxD3ZjGm8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:30.749274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03283","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fc0a4b74ea75f6dd281d893aa6f4d18429dce13db2c32e6731f38cb8b3f955c","sha256:f3946a08bffb8009f97cb0581f1343aef5853710f089a8a34ecfbcc8455907d5"],"state_sha256":"d24f146f38873dcbe504e783fbe6ba83e3f5f4c18abd385f4396c332ed9b2cae"}