{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LGXTNJ7JOSGRVSRQ2DOJVIWKJC","short_pith_number":"pith:LGXTNJ7J","schema_version":"1.0","canonical_sha256":"59af36a7e9748d1aca30d0dc9aa2ca489ce4e8394d73c91c17df3db44d1f6c1c","source":{"kind":"arxiv","id":"2608.00011","version":1},"attestation_state":"computed","paper":{"title":"DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akshat Mandloi, Apoorv Singh, Hamees Sayed, Nityanand Mathur, Sameer Khurana, Sudarshan Kamath, Wasim Madha","submitted_at":"2026-06-19T17:35:42Z","abstract_excerpt":"Current text-to-speech systems face a trade-off: autoregres- sive codec language models produce highly intelligible speech but require large-scale models and training data and decode tokens sequentially, while non-autoregressive approaches im- prove speed at the cost of linguistic accuracy. We present DLLM-TTS, a framework that formulates TTS as conditional block discrete diffusion over X-Codec2 neural audio codec to- kens. The model decomposes sequences into blocks and applies masked diffusion within each block while processing blocks se- quentially, learning both local acoustic coherence and"},"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":"2608.00011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T17:35:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c23e7ac7cbca2e32698bc5667d09cdcf0bfa42718ca677fbb84c020b8e0c17c","abstract_canon_sha256":"2454ec888cbe8b8250f17bb10c63ad98bcf6d5f68bccf168d89a6984049d8d9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:31:37.958477Z","signature_b64":"AvAdfJ5nFVY0ilU4apY42ABNb6wHVqwJ2w9/vG4JRnCgsJRvOwO0JjL5hQ2HuokdbAT3OAVkl1lwna1Cxx7iCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59af36a7e9748d1aca30d0dc9aa2ca489ce4e8394d73c91c17df3db44d1f6c1c","last_reissued_at":"2026-08-04T00:31:37.956993Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:31:37.956993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akshat Mandloi, Apoorv Singh, Hamees Sayed, Nityanand Mathur, Sameer Khurana, Sudarshan Kamath, Wasim Madha","submitted_at":"2026-06-19T17:35:42Z","abstract_excerpt":"Current text-to-speech systems face a trade-off: autoregres- sive codec language models produce highly intelligible speech but require large-scale models and training data and decode tokens sequentially, while non-autoregressive approaches im- prove speed at the cost of linguistic accuracy. We present DLLM-TTS, a framework that formulates TTS as conditional block discrete diffusion over X-Codec2 neural audio codec to- kens. The model decomposes sequences into blocks and applies masked diffusion within each block while processing blocks se- quentially, learning both local acoustic coherence and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00011","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/2608.00011/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":"2608.00011","created_at":"2026-08-04T00:31:37.957994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00011v1","created_at":"2026-08-04T00:31:37.957994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00011","created_at":"2026-08-04T00:31:37.957994+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGXTNJ7JOSGR","created_at":"2026-08-04T00:31:37.957994+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGXTNJ7JOSGRVSRQ","created_at":"2026-08-04T00:31:37.957994+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGXTNJ7J","created_at":"2026-08-04T00:31:37.957994+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/LGXTNJ7JOSGRVSRQ2DOJVIWKJC","json":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC.json","graph_json":"https://pith.science/api/pith-number/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/graph.json","events_json":"https://pith.science/api/pith-number/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/events.json","paper":"https://pith.science/paper/LGXTNJ7J"},"agent_actions":{"view_html":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC","download_json":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC.json","view_paper":"https://pith.science/paper/LGXTNJ7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00011&json=true","fetch_graph":"https://pith.science/api/pith-number/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/graph.json","fetch_events":"https://pith.science/api/pith-number/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/action/storage_attestation","attest_author":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/action/author_attestation","sign_citation":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/action/citation_signature","submit_replication":"https://pith.science/pith/LGXTNJ7JOSGRVSRQ2DOJVIWKJC/action/replication_record"}},"created_at":"2026-08-04T00:31:37.957994+00:00","updated_at":"2026-08-04T00:31:37.957994+00:00"}