{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L4AN2L5ZLPKZYRIIMQ2PQI4FD3","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":"ac607cc65c403bb4f8b752466198fb4327313812913079fae77ffeabf8245097","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-09T19:05:48Z","title_canon_sha256":"d7fdc350fef70bb00d3ada9ffe5e457a08ac6b2ea0b54b5f8d85da3cfd060f44"},"schema_version":"1.0","source":{"id":"2403.05989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05989","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05989v1","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05989","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"L4AN2L5ZLPKZ","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"L4AN2L5ZLPKZYRII","created_at":"2026-07-05T07:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"L4AN2L5Z","created_at":"2026-07-05T07:54:16Z"}],"graph_snapshots":[{"event_id":"sha256:16a08a95f7a665e42da829f5f03c0c0683e5529347d5e3198a5883995f54d8f0","target":"graph","created_at":"2026-07-05T07:54:16Z","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/2403.05989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for diverse training data. In response, we introduce a novel hierarchical acoustic modeling approach complemented by a tailored data augmentation strategy and train it on the combination of real and synthetic data, scaling the data size up to 650k hours, leading to the zero-shot TTS model with 0.8B parameters. Specifically, our method incorporates a latent variabl","authors_text":"Bowen Zhang, Chang Zeng, Chunhui Wang, Jian Zhao, Yefan Zhu, Yong Chen, Zhonglin Jiang, Zifeng Cai, Ziyang Ma","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-09T19:05:48Z","title":"HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05989","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":"sha256:74151d25cbf886f922ed33d68cb9b35d031516b5d2fdf255e4beb285f16243e3","target":"record","created_at":"2026-07-05T07:54:16Z","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":"ac607cc65c403bb4f8b752466198fb4327313812913079fae77ffeabf8245097","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-09T19:05:48Z","title_canon_sha256":"d7fdc350fef70bb00d3ada9ffe5e457a08ac6b2ea0b54b5f8d85da3cfd060f44"},"schema_version":"1.0","source":{"id":"2403.05989","kind":"arxiv","version":1}},"canonical_sha256":"5f00dd2fb95bd59c45086434f823851ecf6a6eabfc654b022fbdc45aab1d88a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f00dd2fb95bd59c45086434f823851ecf6a6eabfc654b022fbdc45aab1d88a0","first_computed_at":"2026-07-05T07:54:16.434609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:16.434609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lr7yQuHXu3mhfaWnrXAzv3+Geceua0v7s9feTIr8kPvHPrSZnEwctS20rVz0vdlxMzdcQwFc+gGtokBZdJzHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:16.435076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.05989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74151d25cbf886f922ed33d68cb9b35d031516b5d2fdf255e4beb285f16243e3","sha256:16a08a95f7a665e42da829f5f03c0c0683e5529347d5e3198a5883995f54d8f0"],"state_sha256":"33809dafcdf4ba518eb6238261bb17eef4e5266f2b8d7c7d23dbed0e93221072"}