{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3R5AFDRKESZXTF3WGXZDICLXO5","short_pith_number":"pith:3R5AFDRK","schema_version":"1.0","canonical_sha256":"dc7a028e2a24b379977635f23409777773dba374129dfb01ac20ae60983cb8c1","source":{"kind":"arxiv","id":"2607.06461","version":1},"attestation_state":"computed","paper":{"title":"WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengbin Jin, Deyi Tuo, Jialong Mai, Jinxin Ji, Sihang Nie, Xiangmin Xu, Xiaofen Xing","submitted_at":"2026-07-07T16:22:59Z","abstract_excerpt":"While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and strict temporal alignment, such as audiobook narration and video dubbing, the inability to explicitly manipulate word-level acoustic attributes remains a critical bottleneck. This limitation is primarily amplified by the severe scarcity of fine-grained annotated datasets and the architectural challenge of integrating mul"},"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":"2607.06461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-07T16:22:59Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a583abed5c46a11b0ac43ac306db686e803a6f2db3ae4dda893384bb474c87f4","abstract_canon_sha256":"62da06ffd83b3b1d9da23854a26ad2eb547264fd2eb4ed9525f1cb54cbd330a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:26.924788Z","signature_b64":"13D1LcumecdGeMbLYVzjtd433UUe5C34GFTdBd/9uFjlD8dcdKMKO5oDyxfP2EFDhg2mAVl72VL3UBRO9/QkDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc7a028e2a24b379977635f23409777773dba374129dfb01ac20ae60983cb8c1","last_reissued_at":"2026-07-08T01:19:26.924359Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:26.924359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengbin Jin, Deyi Tuo, Jialong Mai, Jinxin Ji, Sihang Nie, Xiangmin Xu, Xiaofen Xing","submitted_at":"2026-07-07T16:22:59Z","abstract_excerpt":"While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and strict temporal alignment, such as audiobook narration and video dubbing, the inability to explicitly manipulate word-level acoustic attributes remains a critical bottleneck. This limitation is primarily amplified by the severe scarcity of fine-grained annotated datasets and the architectural challenge of integrating mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06461","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/2607.06461/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":"2607.06461","created_at":"2026-07-08T01:19:26.924424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06461v1","created_at":"2026-07-08T01:19:26.924424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06461","created_at":"2026-07-08T01:19:26.924424+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R5AFDRKESZX","created_at":"2026-07-08T01:19:26.924424+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R5AFDRKESZXTF3W","created_at":"2026-07-08T01:19:26.924424+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R5AFDRK","created_at":"2026-07-08T01:19:26.924424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06461","citing_title":"WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5","json":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5.json","graph_json":"https://pith.science/api/pith-number/3R5AFDRKESZXTF3WGXZDICLXO5/graph.json","events_json":"https://pith.science/api/pith-number/3R5AFDRKESZXTF3WGXZDICLXO5/events.json","paper":"https://pith.science/paper/3R5AFDRK"},"agent_actions":{"view_html":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5","download_json":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5.json","view_paper":"https://pith.science/paper/3R5AFDRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06461&json=true","fetch_graph":"https://pith.science/api/pith-number/3R5AFDRKESZXTF3WGXZDICLXO5/graph.json","fetch_events":"https://pith.science/api/pith-number/3R5AFDRKESZXTF3WGXZDICLXO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5/action/storage_attestation","attest_author":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5/action/author_attestation","sign_citation":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5/action/citation_signature","submit_replication":"https://pith.science/pith/3R5AFDRKESZXTF3WGXZDICLXO5/action/replication_record"}},"created_at":"2026-07-08T01:19:26.924424+00:00","updated_at":"2026-07-08T01:19:26.924424+00:00"}