{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CQIEHCBUILFIKMRZYX4NUTKIB","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":"1f5745ef35deb3c2db33927a40f595ebbbc3d2be1a6fc2661152640eb8bb00f6","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T06:43:34Z","title_canon_sha256":"ed35e97aca7145d08f55b0f3f1c3b48a9d5e407b027740d3be6d6e6ae5bb1e86"},"schema_version":"1.0","source":{"id":"2406.02009","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02009","created_at":"2026-07-05T08:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02009v2","created_at":"2026-07-05T08:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02009","created_at":"2026-07-05T08:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"6CQIEHCBUILF","created_at":"2026-07-05T08:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"6CQIEHCBUILFIKMR","created_at":"2026-07-05T08:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"6CQIEHCB","created_at":"2026-07-05T08:30:34Z"}],"graph_snapshots":[{"event_id":"sha256:f94d4252a28fd2f9ccabd9bc1248cef605b37a5cc54ed8b937da5fa09ad4d046","target":"graph","created_at":"2026-07-05T08:30:34Z","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/2406.02009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the accumulation of errors in speech unit predictions during autoregressive language modeling. In this paper, we propose a phonetic enhanced language modeling method to improve the performance of TTS models. We leverage self-supervised representations that are phonetically rich as the training target for the autoregressive language model. Subsequently, a non-autoregressive model is employed to predict discrete acoustic code","authors_text":"Bin Ma, Chongjia Ni, Chong Zhang, Dianwen Ng, Hao Wang, Jia Qi Yip, Kun Zhou, Nguyen Trung Hieu, Shengkui Zhao, Yukun Ma","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T06:43:34Z","title":"Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02009","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":"sha256:37177d87a4fad891e070b91134d19b25e715300c928669c81a65913ca319ce8a","target":"record","created_at":"2026-07-05T08:30:34Z","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":"1f5745ef35deb3c2db33927a40f595ebbbc3d2be1a6fc2661152640eb8bb00f6","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-04T06:43:34Z","title_canon_sha256":"ed35e97aca7145d08f55b0f3f1c3b48a9d5e407b027740d3be6d6e6ae5bb1e86"},"schema_version":"1.0","source":{"id":"2406.02009","kind":"arxiv","version":2}},"canonical_sha256":"f0a0821c41a216542991ce2fc6d26a40608ab544712c1b33695a45aaaac3627e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0a0821c41a216542991ce2fc6d26a40608ab544712c1b33695a45aaaac3627e","first_computed_at":"2026-07-05T08:30:34.029308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:34.029308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KSUxEgVRgIZ+dDav+GwnFZiBwXn06dqZlUsXq+iC5335EB6Y83hZwSer58yeghQrq+3Jrkro6hF0QBGmqFUuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:34.029942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02009","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37177d87a4fad891e070b91134d19b25e715300c928669c81a65913ca319ce8a","sha256:f94d4252a28fd2f9ccabd9bc1248cef605b37a5cc54ed8b937da5fa09ad4d046"],"state_sha256":"ca47ec1977a55eb15f8d05fa421de6953480218efcbed82ff2dc318131ef7a51"}