{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ELXX4LG4BCLKCYEH45WRGW4MG3","short_pith_number":"pith:ELXX4LG4","schema_version":"1.0","canonical_sha256":"22ef7e2cdc0896a16087e76d135b8c36f1c820de9304b573012cd16fa49d5113","source":{"kind":"arxiv","id":"2503.20499","version":3},"attestation_state":"computed","paper":{"title":"FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Fei-Yu Shen, Feng-Long Xie, Hao-Han Guo, Kun Xie, Xu Tang, Yao Hu, Yi-Chen Wu","submitted_at":"2025-03-26T12:39:06Z","abstract_excerpt":"In this work, we upgrade FireRedTTS to a new version, FireRedTTS-1S, a high-quality streaming foundation text-to-speech system. FireRedTTS-1S achieves streaming speech generation via two steps: text-to-semantic decoding and semantic-to-acoustic decoding. In text-to-semantic decoding, a semantic-aware speech tokenizer converts the speech signal into semantic tokens, which can be synthesized from the text via a language model in an auto-regressive manner. Meanwhile, the semantic-to-acoustic decoding module simultaneously translates generated semantic tokens into the speech signal in a streaming "},"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":"2503.20499","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-26T12:39:06Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"43090d8e1dcdc740d03c16b8cf5528488cd38cc97d23428b77a957d7006beda4","abstract_canon_sha256":"381d43e7efc17d0b4e99a4e8bc1971ef45139ef78d7df387e8ad40545ba7b4f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:46.287783Z","signature_b64":"levZZqDG7EWWPBQDw31eZJprwyPfrxGcjrh5cpKH7qnsnlYq50oTUzEHkx82vr8/0L+fu6tQVwWBw/DO3otnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22ef7e2cdc0896a16087e76d135b8c36f1c820de9304b573012cd16fa49d5113","last_reissued_at":"2026-07-05T11:09:46.287298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:46.287298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Fei-Yu Shen, Feng-Long Xie, Hao-Han Guo, Kun Xie, Xu Tang, Yao Hu, Yi-Chen Wu","submitted_at":"2025-03-26T12:39:06Z","abstract_excerpt":"In this work, we upgrade FireRedTTS to a new version, FireRedTTS-1S, a high-quality streaming foundation text-to-speech system. FireRedTTS-1S achieves streaming speech generation via two steps: text-to-semantic decoding and semantic-to-acoustic decoding. In text-to-semantic decoding, a semantic-aware speech tokenizer converts the speech signal into semantic tokens, which can be synthesized from the text via a language model in an auto-regressive manner. Meanwhile, the semantic-to-acoustic decoding module simultaneously translates generated semantic tokens into the speech signal in a streaming "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20499","kind":"arxiv","version":3},"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/2503.20499/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":"2503.20499","created_at":"2026-07-05T11:09:46.287365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20499v3","created_at":"2026-07-05T11:09:46.287365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20499","created_at":"2026-07-05T11:09:46.287365+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELXX4LG4BCLK","created_at":"2026-07-05T11:09:46.287365+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELXX4LG4BCLKCYEH","created_at":"2026-07-05T11:09:46.287365+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELXX4LG4","created_at":"2026-07-05T11:09:46.287365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.15148","citing_title":"XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17958","citing_title":"MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3","json":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3.json","graph_json":"https://pith.science/api/pith-number/ELXX4LG4BCLKCYEH45WRGW4MG3/graph.json","events_json":"https://pith.science/api/pith-number/ELXX4LG4BCLKCYEH45WRGW4MG3/events.json","paper":"https://pith.science/paper/ELXX4LG4"},"agent_actions":{"view_html":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3","download_json":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3.json","view_paper":"https://pith.science/paper/ELXX4LG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20499&json=true","fetch_graph":"https://pith.science/api/pith-number/ELXX4LG4BCLKCYEH45WRGW4MG3/graph.json","fetch_events":"https://pith.science/api/pith-number/ELXX4LG4BCLKCYEH45WRGW4MG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3/action/storage_attestation","attest_author":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3/action/author_attestation","sign_citation":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3/action/citation_signature","submit_replication":"https://pith.science/pith/ELXX4LG4BCLKCYEH45WRGW4MG3/action/replication_record"}},"created_at":"2026-07-05T11:09:46.287365+00:00","updated_at":"2026-07-05T11:09:46.287365+00:00"}