{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CUBBUHJAOY5KWI6Q46UVZXLN4Y","short_pith_number":"pith:CUBBUHJA","schema_version":"1.0","canonical_sha256":"15021a1d20763aab23d0e7a95cdd6de6313e4b49410e632178697fa126f20ff9","source":{"kind":"arxiv","id":"2607.04140","version":1},"attestation_state":"computed","paper":{"title":"DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Heeseung Kim, Hoseong Ahn, Junwon Moon, Kyuhong Shim, Seungbeom Kim, Sewoong Park, Yejin Lee","submitted_at":"2026-07-05T06:45:47Z","abstract_excerpt":"Autoregressive (AR) text-to-speech (TTS) models generate discrete speech tokens sequentially, which makes inference slow and can degrade robustness by propagating local errors and hallucinations. This limitation stems from their left-to-right AR commitment: each token must be determined before future speech-token context is available. However, such ordering is not an inherent requirement for TTS, as the full input text is available before synthesis. In this paper, we introduce DELTA-TTS, a lightweight LoRA-based adaptation framework that converts a pretrained AR TTS model into a discrete diffu"},"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":"2607.04140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-05T06:45:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b1fb7da9b85ba71be48f773af75284c031285e590fe90d3422c9c67d7f215e1d","abstract_canon_sha256":"c462772e79f75b54a6c04930b774c9202b34e1ffa61c169c22ffeef05263c25d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:59.327778Z","signature_b64":"ZQVfYrUYW9GTdYg9PKUcWBb3vc3BanwcyNUjjGuAECVYu5irLWJ450m9GLp74slbNqBqd0Glxu1MbezaMmOCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15021a1d20763aab23d0e7a95cdd6de6313e4b49410e632178697fa126f20ff9","last_reissued_at":"2026-07-07T02:18:59.326975Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:59.326975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Heeseung Kim, Hoseong Ahn, Junwon Moon, Kyuhong Shim, Seungbeom Kim, Sewoong Park, Yejin Lee","submitted_at":"2026-07-05T06:45:47Z","abstract_excerpt":"Autoregressive (AR) text-to-speech (TTS) models generate discrete speech tokens sequentially, which makes inference slow and can degrade robustness by propagating local errors and hallucinations. This limitation stems from their left-to-right AR commitment: each token must be determined before future speech-token context is available. However, such ordering is not an inherent requirement for TTS, as the full input text is available before synthesis. In this paper, we introduce DELTA-TTS, a lightweight LoRA-based adaptation framework that converts a pretrained AR TTS model into a discrete diffu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04140","kind":"arxiv","version":1},"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/2607.04140/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":"2607.04140","created_at":"2026-07-07T02:18:59.327097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04140v1","created_at":"2026-07-07T02:18:59.327097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04140","created_at":"2026-07-07T02:18:59.327097+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUBBUHJAOY5K","created_at":"2026-07-07T02:18:59.327097+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUBBUHJAOY5KWI6Q","created_at":"2026-07-07T02:18:59.327097+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUBBUHJA","created_at":"2026-07-07T02:18:59.327097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y","json":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y.json","graph_json":"https://pith.science/api/pith-number/CUBBUHJAOY5KWI6Q46UVZXLN4Y/graph.json","events_json":"https://pith.science/api/pith-number/CUBBUHJAOY5KWI6Q46UVZXLN4Y/events.json","paper":"https://pith.science/paper/CUBBUHJA"},"agent_actions":{"view_html":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y","download_json":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y.json","view_paper":"https://pith.science/paper/CUBBUHJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04140&json=true","fetch_graph":"https://pith.science/api/pith-number/CUBBUHJAOY5KWI6Q46UVZXLN4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/CUBBUHJAOY5KWI6Q46UVZXLN4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y/action/storage_attestation","attest_author":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y/action/author_attestation","sign_citation":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y/action/citation_signature","submit_replication":"https://pith.science/pith/CUBBUHJAOY5KWI6Q46UVZXLN4Y/action/replication_record"}},"created_at":"2026-07-07T02:18:59.327097+00:00","updated_at":"2026-07-07T02:18:59.327097+00:00"}