{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BJ5JZDPI63HWLIHI4UQIPAAY5G","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":"fa66cd07bb16dc211caf26a67f3a8adb080fd4f75080ff4ebbb453f089f292f9","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T06:55:03Z","title_canon_sha256":"5c0251c6303d0d0325cff1fe8406705d18bd3f69033c1b7a83af43470cf041d0"},"schema_version":"1.0","source":{"id":"2307.00782","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00782","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00782v2","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00782","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"pith_short_12","alias_value":"BJ5JZDPI63HW","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"pith_short_16","alias_value":"BJ5JZDPI63HWLIHI","created_at":"2026-07-05T06:58:11Z"},{"alias_kind":"pith_short_8","alias_value":"BJ5JZDPI","created_at":"2026-07-05T06:58:11Z"}],"graph_snapshots":[{"event_id":"sha256:a088837db8076f5640a0e0c33fe7da14815ae61465f74569bd49d06fde6354ff","target":"graph","created_at":"2026-07-05T06:58:11Z","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/2307.00782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i) ignorance of cross-sentence contextual information, and ii) high computation and memory cost for long-form synthesis. To address these issues, this work develops a lightweight yet effective TTS system, ContextSpeech. Specifically, we first design a memory-cached recurrence mechanism to incorporate global text and speech context into sentence encoding. Then we con","authors_text":"Frank K. Soong, Lei He, Shaofei Zhang, Sheng Zhao, Tan Lee, Xi Wang, Xu Tan, Yujia Xiao","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T06:55:03Z","title":"ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00782","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":"sha256:3248090a69cb658eacf7cf30d26b9f141e8b6ecce045317147db54033f129477","target":"record","created_at":"2026-07-05T06:58:11Z","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":"fa66cd07bb16dc211caf26a67f3a8adb080fd4f75080ff4ebbb453f089f292f9","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T06:55:03Z","title_canon_sha256":"5c0251c6303d0d0325cff1fe8406705d18bd3f69033c1b7a83af43470cf041d0"},"schema_version":"1.0","source":{"id":"2307.00782","kind":"arxiv","version":2}},"canonical_sha256":"0a7a9c8de8f6cf65a0e8e520878018e987ef69b5f01cc8dbc537d1dc8ea76c42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a7a9c8de8f6cf65a0e8e520878018e987ef69b5f01cc8dbc537d1dc8ea76c42","first_computed_at":"2026-07-05T06:58:11.537917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:11.537917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PO1Yuose5UFg+MicGn6QS8C0FQzRELe3DvFLiZE1mR9JgOXTyuX0alyPgvg98Togk2WmzMsAOrs7dv6m4jDUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:11.538363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00782","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3248090a69cb658eacf7cf30d26b9f141e8b6ecce045317147db54033f129477","sha256:a088837db8076f5640a0e0c33fe7da14815ae61465f74569bd49d06fde6354ff"],"state_sha256":"34a90642eb9207dc9247a9a6f40861d4e691c3e68646c940c0f111536c0bd3a3"}