{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XMXLN3AW5GPDERU46DJGKUU3TW","short_pith_number":"pith:XMXLN3AW","schema_version":"1.0","canonical_sha256":"bb2eb6ec16e99e32469cf0d265529b9db874d824f61db5a1f7352808ad439b6c","source":{"kind":"arxiv","id":"2409.03283","version":2},"attestation_state":"computed","paper":{"title":"FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications","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, Kai-Tuo Xu, Kun Liu, Kun Xie, Xu Tang, Yao Hu, Yi-Chen Wu","submitted_at":"2024-09-05T06:48:02Z","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"},"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":"2409.03283","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-05T06:48:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5e01eda909f4e14a78cf555436330df01af86d472b9670aab6d4f608ca9f1651","abstract_canon_sha256":"3c9ca8cdff5d88d0439271f62c07df3fe61375b79c02e863b8e2dc3f9b41bbcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:30.749274Z","signature_b64":"wKUAmn+NbGa0+geyIWAuZ8bbSPs5fQyAf34HerMXy5s8zSO1ypZlVusxUtytkcsHUjV3u1djegFFxD3ZjGm8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2eb6ec16e99e32469cf0d265529b9db874d824f61db5a1f7352808ad439b6c","last_reissued_at":"2026-07-05T10:47:30.748793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:30.748793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications","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, Kai-Tuo Xu, Kun Liu, Kun Xie, Xu Tang, Yao Hu, Yi-Chen Wu","submitted_at":"2024-09-05T06:48:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03283","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/2409.03283/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":"2409.03283","created_at":"2026-07-05T10:47:30.748851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03283v2","created_at":"2026-07-05T10:47:30.748851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03283","created_at":"2026-07-05T10:47:30.748851+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMXLN3AW5GPD","created_at":"2026-07-05T10:47:30.748851+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMXLN3AW5GPDERU4","created_at":"2026-07-05T10:47:30.748851+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMXLN3AW","created_at":"2026-07-05T10:47:30.748851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21882","citing_title":"Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18072","citing_title":"One-Step Token-to-Waveform Generation with MeanFlow in Latent Space","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09141","citing_title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09098","citing_title":"HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09234","citing_title":"End-to-End Training for Discrete Token LLM based TTS System","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09019","citing_title":"TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06928","citing_title":"VoxCPM2 Technical Report","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00363","citing_title":"Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03455","citing_title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":45,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23552","citing_title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16964","citing_title":"SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09318","citing_title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.19414","citing_title":"EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01284","citing_title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00688","citing_title":"OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10117","citing_title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW","json":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW.json","graph_json":"https://pith.science/api/pith-number/XMXLN3AW5GPDERU46DJGKUU3TW/graph.json","events_json":"https://pith.science/api/pith-number/XMXLN3AW5GPDERU46DJGKUU3TW/events.json","paper":"https://pith.science/paper/XMXLN3AW"},"agent_actions":{"view_html":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW","download_json":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW.json","view_paper":"https://pith.science/paper/XMXLN3AW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03283&json=true","fetch_graph":"https://pith.science/api/pith-number/XMXLN3AW5GPDERU46DJGKUU3TW/graph.json","fetch_events":"https://pith.science/api/pith-number/XMXLN3AW5GPDERU46DJGKUU3TW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW/action/storage_attestation","attest_author":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW/action/author_attestation","sign_citation":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW/action/citation_signature","submit_replication":"https://pith.science/pith/XMXLN3AW5GPDERU46DJGKUU3TW/action/replication_record"}},"created_at":"2026-07-05T10:47:30.748851+00:00","updated_at":"2026-07-05T10:47:30.748851+00:00"}