{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCQXYJVXW4HTRLJMOZRTZDUSZG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3b0a1c09c52712a9f9542713851beb79a66bd6792c1bcfefe6a6f6b214185f88","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T01:31:19Z","title_canon_sha256":"292b292dc4b0d23dd29c67ff35cc1851b6207ac9c66870cb137ece9e72710ba9"},"schema_version":"1.0","source":{"id":"2409.11630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11630","created_at":"2026-07-05T09:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11630v1","created_at":"2026-07-05T09:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11630","created_at":"2026-07-05T09:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"NCQXYJVXW4HT","created_at":"2026-07-05T09:08:34Z"},{"alias_kind":"pith_short_16","alias_value":"NCQXYJVXW4HTRLJM","created_at":"2026-07-05T09:08:34Z"},{"alias_kind":"pith_short_8","alias_value":"NCQXYJVX","created_at":"2026-07-05T09:08:34Z"}],"graph_snapshots":[{"event_id":"sha256:6dbd0d79b47eefa8dfd8d4cd9434ac96c10b9e98566968dbe0f61d8e34ca9b0e","target":"graph","created_at":"2026-07-05T09:08:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.11630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The neural codec language model (CLM) has demonstrated remarkable performance in text-to-speech (TTS) synthesis. However, troubled by ``recency bias\", CLM lacks sufficient attention to coarse-grained information at a higher temporal scale, often producing unnatural or even unintelligible speech. This work proposes CoFi-Speech, a coarse-to-fine CLM-TTS approach, employing multi-scale speech coding and generation to address this issue. We train a multi-scale neural codec, CoFi-Codec, to encode speech into a multi-scale discrete representation, comprising multiple token sequences with different t","authors_text":"Dongchao Yang, Fenglong Xie, Haohan Guo, Helen Meng, Xixin Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T01:31:19Z","title":"Speaking from Coarse to Fine: Improving Neural Codec Language Model via Multi-Scale Speech Coding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11630","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c5922faa3d4de7e0f631dd681fa79e32e0be8b411a5b997bec00a32c2cf12916","target":"record","created_at":"2026-07-05T09:08:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3b0a1c09c52712a9f9542713851beb79a66bd6792c1bcfefe6a6f6b214185f88","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T01:31:19Z","title_canon_sha256":"292b292dc4b0d23dd29c67ff35cc1851b6207ac9c66870cb137ece9e72710ba9"},"schema_version":"1.0","source":{"id":"2409.11630","kind":"arxiv","version":1}},"canonical_sha256":"68a17c26b7b70f38ad2c76633c8e92c99a59fa4013e797294df04262bc0236a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68a17c26b7b70f38ad2c76633c8e92c99a59fa4013e797294df04262bc0236a9","first_computed_at":"2026-07-05T09:08:34.992204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:34.992204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"um99gkTq1Ub8FPKyUP4v/pdcGuW6qaYiRBJweaAFTfMNW5kPGLVjqF7ieMTB1QNWEL0nle9IhYAuuoLHowSzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:34.992683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5922faa3d4de7e0f631dd681fa79e32e0be8b411a5b997bec00a32c2cf12916","sha256:6dbd0d79b47eefa8dfd8d4cd9434ac96c10b9e98566968dbe0f61d8e34ca9b0e"],"state_sha256":"3a82dedfde47f3da690157cb809df26fa8722a5f7890a8f2e78424e6bdb9395c"}