{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UC3YL543YVYZRSBWHLO6JPYOPE","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":"2334d4140db57e48de2f24e4404a65c8636c464a0eccad802d7a5ecd94a2d3d2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-22T06:39:52Z","title_canon_sha256":"607f218fc676441ae8bcc1e81715ccdba031649e303c92357bd749a507ca74d5"},"schema_version":"1.0","source":{"id":"2406.15752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15752","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15752v1","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15752","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_12","alias_value":"UC3YL543YVYZ","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_16","alias_value":"UC3YL543YVYZRSBW","created_at":"2026-07-05T08:35:27Z"},{"alias_kind":"pith_short_8","alias_value":"UC3YL543","created_at":"2026-07-05T08:35:27Z"}],"graph_snapshots":[{"event_id":"sha256:1c2d1d455eff5d7da3892cdde3e33b76e6ef52552d7962873ada75b8ecebfa27","target":"graph","created_at":"2026-07-05T08:35:27Z","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/2406.15752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural codec language model (LM) has demonstrated strong capability in zero-shot text-to-speech (TTS) synthesis. However, the codec LM often suffers from limitations in inference speed and stability, due to its auto-regressive nature and implicit alignment between text and audio. In this work, to handle these challenges, we introduce a new variant of neural codec LM, namely TacoLM. Specifically, TacoLM introduces a gated attention mechanism to improve the training and inference efficiency and reduce the model size. Meanwhile, an additional gated cross-attention layer is included for each decod","authors_text":"Guanrou Yang, Xiaofei Wang, Xie Chen, Yakun Song, Zhuo Chen, Ziyang Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-22T06:39:52Z","title":"TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15752","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":"sha256:6cbf7ea39b3348685e4bce4c868faad34f367d74fa5ee86a18b1921c0fedd11d","target":"record","created_at":"2026-07-05T08:35:27Z","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":"2334d4140db57e48de2f24e4404a65c8636c464a0eccad802d7a5ecd94a2d3d2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-22T06:39:52Z","title_canon_sha256":"607f218fc676441ae8bcc1e81715ccdba031649e303c92357bd749a507ca74d5"},"schema_version":"1.0","source":{"id":"2406.15752","kind":"arxiv","version":1}},"canonical_sha256":"a0b785f79bc57198c8363adde4bf0e79163e03d9a7a0ca4146960df13a1d0502","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0b785f79bc57198c8363adde4bf0e79163e03d9a7a0ca4146960df13a1d0502","first_computed_at":"2026-07-05T08:35:27.042212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:27.042212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QuEtqr3HBP0Nc4od9ZbDDFltXBVavQKdJX6OBJmRoTbzhk+Gml7/7rtMjhWY8KEbhqryx7ujrrO2qIp7o9rDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:27.042708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cbf7ea39b3348685e4bce4c868faad34f367d74fa5ee86a18b1921c0fedd11d","sha256:1c2d1d455eff5d7da3892cdde3e33b76e6ef52552d7962873ada75b8ecebfa27"],"state_sha256":"6df0b585a8c13a86ca38e0b300883db4aa70be67a5c39f37646c34f982ede3a4"}