{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XAISI4M5OS5RSHFOQ5LO7VWDP3","short_pith_number":"pith:XAISI4M5","schema_version":"1.0","canonical_sha256":"b81124719d74bb191cae8756efd6c37ee11a7147c7248f370c20f316d9a58d1d","source":{"kind":"arxiv","id":"2406.11427","version":2},"attestation_state":"computed","paper":{"title":"DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors","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":"Dong Won Kim, Jaehyeon Kim, Jaewoong Cho, Keon Lee, Seungjun Chung","submitted_at":"2024-06-17T11:25:57Z","abstract_excerpt":"Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. While recent studies show potential in removing these domain-specific factors, performance remains suboptimal. In this work, we introduce DiTTo-TTS, a Diffusion Transformer (DiT)-based TTS model, to investigate whether LDM-based TTS can achieve state-of-the-art performance without domain-specific factors. Through rigorous analysis and empirical exploration, we find that (1) DiT wit"},"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":"2406.11427","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T11:25:57Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"35ff7028f2d7f364fdc2ad9c9921e745a459732dcf9a1ef40face9c5b210de52","abstract_canon_sha256":"b6618ce0ec07dfc403d01581dbde475b8a9bb085cb551d0cf945cad55024a36a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:17.500461Z","signature_b64":"V7Q0D2+Hgphfvw0wgzAKUMC1DynOmw/9wu6Ns8v6zUtMxvmeO4dK3IGHK2Xg65l+wjZj+4a5yuVnbMoaBKN8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b81124719d74bb191cae8756efd6c37ee11a7147c7248f370c20f316d9a58d1d","last_reissued_at":"2026-07-05T10:15:17.499946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:17.499946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors","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":"Dong Won Kim, Jaehyeon Kim, Jaewoong Cho, Keon Lee, Seungjun Chung","submitted_at":"2024-06-17T11:25:57Z","abstract_excerpt":"Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. While recent studies show potential in removing these domain-specific factors, performance remains suboptimal. In this work, we introduce DiTTo-TTS, a Diffusion Transformer (DiT)-based TTS model, to investigate whether LDM-based TTS can achieve state-of-the-art performance without domain-specific factors. Through rigorous analysis and empirical exploration, we find that (1) DiT wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11427","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/2406.11427/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":"2406.11427","created_at":"2026-07-05T10:15:17.500012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11427v2","created_at":"2026-07-05T10:15:17.500012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11427","created_at":"2026-07-05T10:15:17.500012+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAISI4M5OS5R","created_at":"2026-07-05T10:15:17.500012+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAISI4M5OS5RSHFO","created_at":"2026-07-05T10:15:17.500012+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAISI4M5","created_at":"2026-07-05T10:15:17.500012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11611","citing_title":"SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23552","citing_title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20830","citing_title":"Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech","ref_index":16,"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":114,"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":23,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10117","citing_title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3","json":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3.json","graph_json":"https://pith.science/api/pith-number/XAISI4M5OS5RSHFOQ5LO7VWDP3/graph.json","events_json":"https://pith.science/api/pith-number/XAISI4M5OS5RSHFOQ5LO7VWDP3/events.json","paper":"https://pith.science/paper/XAISI4M5"},"agent_actions":{"view_html":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3","download_json":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3.json","view_paper":"https://pith.science/paper/XAISI4M5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11427&json=true","fetch_graph":"https://pith.science/api/pith-number/XAISI4M5OS5RSHFOQ5LO7VWDP3/graph.json","fetch_events":"https://pith.science/api/pith-number/XAISI4M5OS5RSHFOQ5LO7VWDP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3/action/storage_attestation","attest_author":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3/action/author_attestation","sign_citation":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3/action/citation_signature","submit_replication":"https://pith.science/pith/XAISI4M5OS5RSHFOQ5LO7VWDP3/action/replication_record"}},"created_at":"2026-07-05T10:15:17.500012+00:00","updated_at":"2026-07-05T10:15:17.500012+00:00"}