{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZHJGOSJM25WFYPLFK3YMLQHCWY","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":"a4cf57410dbe3931c88543c25b50fec5bdb3cf5b62d30fc88da1d98d417eb342","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T02:18:45Z","title_canon_sha256":"649896ef10acd555baaf589589d8816a251d90e5b110f574416663517995a060"},"schema_version":"1.0","source":{"id":"2505.13830","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13830","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13830v2","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13830","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZHJGOSJM25WF","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZHJGOSJM25WFYPLF","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZHJGOSJM","created_at":"2026-07-05T11:07:25Z"}],"graph_snapshots":[{"event_id":"sha256:14001423e43f433591105d82f52464f7d732ae967aec179985e54b9d77fbe5cd","target":"graph","created_at":"2026-07-05T11:07:25Z","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/2505.13830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) based zero-shot text-to-speech (TTS) methods tend to preserve the acoustic environment of the audio prompt, leading to degradation in synthesized speech quality when the audio prompt contains noise. In this paper, we propose a novel neural codec-based speech denoiser and integrate it with the advanced LLM-based TTS model, LauraTTS, to achieve noise-robust zero-shot TTS. The proposed codec denoiser consists of an audio codec, a token denoiser, and an embedding refiner. The token denoiser predicts the first two groups of clean acoustic tokens from the noisy ones, which","authors_text":"Fei Liu, Hui-Peng Du, Yang Ai, Ye-Xin Lu, Zhen-Hua Ling","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T02:18:45Z","title":"Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13830","kind":"arxiv","version":2},"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":"sha256:4f4e3bd3032fd1812a1d932bdeff3d9c3d4973f4f5d158bd8d3d2134b9a4edd1","target":"record","created_at":"2026-07-05T11:07:25Z","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":"a4cf57410dbe3931c88543c25b50fec5bdb3cf5b62d30fc88da1d98d417eb342","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T02:18:45Z","title_canon_sha256":"649896ef10acd555baaf589589d8816a251d90e5b110f574416663517995a060"},"schema_version":"1.0","source":{"id":"2505.13830","kind":"arxiv","version":2}},"canonical_sha256":"c9d267492cd76c5c3d6556f0c5c0e2b63446bf8f65195e8a7ac0af7f88090bcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9d267492cd76c5c3d6556f0c5c0e2b63446bf8f65195e8a7ac0af7f88090bcb","first_computed_at":"2026-07-05T11:07:25.097110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:25.097110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/UKlBDH/S/8LWPOI88XmnV9L6eD+l9b8AqQtLvcg/MFcnyuO8ATmyJoodZVu80K60NOrygwXektB1dJC9jPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:25.097633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13830","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f4e3bd3032fd1812a1d932bdeff3d9c3d4973f4f5d158bd8d3d2134b9a4edd1","sha256:14001423e43f433591105d82f52464f7d732ae967aec179985e54b9d77fbe5cd"],"state_sha256":"1e419ded0c6c5023ec154610934bbd3eb767af1ff9127cd51274e35600a06082"}