{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L4AN2L5ZLPKZYRIIMQ2PQI4FD3","short_pith_number":"pith:L4AN2L5Z","schema_version":"1.0","canonical_sha256":"5f00dd2fb95bd59c45086434f823851ecf6a6eabfc654b022fbdc45aab1d88a0","source":{"kind":"arxiv","id":"2403.05989","version":1},"attestation_state":"computed","paper":{"title":"HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bowen Zhang, Chang Zeng, Chunhui Wang, Jian Zhao, Yefan Zhu, Yong Chen, Zhonglin Jiang, Zifeng Cai, Ziyang Ma","submitted_at":"2024-03-09T19:05:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.05989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-09T19:05:48Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d7fdc350fef70bb00d3ada9ffe5e457a08ac6b2ea0b54b5f8d85da3cfd060f44","abstract_canon_sha256":"ac607cc65c403bb4f8b752466198fb4327313812913079fae77ffeabf8245097"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:16.435076Z","signature_b64":"Lr7yQuHXu3mhfaWnrXAzv3+Geceua0v7s9feTIr8kPvHPrSZnEwctS20rVz0vdlxMzdcQwFc+gGtokBZdJzHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f00dd2fb95bd59c45086434f823851ecf6a6eabfc654b022fbdc45aab1d88a0","last_reissued_at":"2026-07-05T07:54:16.434609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:16.434609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bowen Zhang, Chang Zeng, Chunhui Wang, Jian Zhao, Yefan Zhu, Yong Chen, Zhonglin Jiang, Zifeng Cai, Ziyang Ma","submitted_at":"2024-03-09T19:05:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05989","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.05989/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.05989","created_at":"2026-07-05T07:54:16.434665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05989v1","created_at":"2026-07-05T07:54:16.434665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05989","created_at":"2026-07-05T07:54:16.434665+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4AN2L5ZLPKZ","created_at":"2026-07-05T07:54:16.434665+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4AN2L5ZLPKZYRII","created_at":"2026-07-05T07:54:16.434665+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4AN2L5Z","created_at":"2026-07-05T07:54:16.434665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3","json":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3.json","graph_json":"https://pith.science/api/pith-number/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/graph.json","events_json":"https://pith.science/api/pith-number/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/events.json","paper":"https://pith.science/paper/L4AN2L5Z"},"agent_actions":{"view_html":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3","download_json":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3.json","view_paper":"https://pith.science/paper/L4AN2L5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05989&json=true","fetch_graph":"https://pith.science/api/pith-number/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/graph.json","fetch_events":"https://pith.science/api/pith-number/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/action/storage_attestation","attest_author":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/action/author_attestation","sign_citation":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/action/citation_signature","submit_replication":"https://pith.science/pith/L4AN2L5ZLPKZYRIIMQ2PQI4FD3/action/replication_record"}},"created_at":"2026-07-05T07:54:16.434665+00:00","updated_at":"2026-07-05T07:54:16.434665+00:00"}