{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BJ5JZDPI63HWLIHI4UQIPAAY5G","short_pith_number":"pith:BJ5JZDPI","schema_version":"1.0","canonical_sha256":"0a7a9c8de8f6cf65a0e8e520878018e987ef69b5f01cc8dbc537d1dc8ea76c42","source":{"kind":"arxiv","id":"2307.00782","version":2},"attestation_state":"computed","paper":{"title":"ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Frank K. Soong, Lei He, Shaofei Zhang, Sheng Zhao, Tan Lee, Xi Wang, Xu Tan, Yujia Xiao","submitted_at":"2023-07-03T06:55:03Z","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"},"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":"2307.00782","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T06:55:03Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5c0251c6303d0d0325cff1fe8406705d18bd3f69033c1b7a83af43470cf041d0","abstract_canon_sha256":"fa66cd07bb16dc211caf26a67f3a8adb080fd4f75080ff4ebbb453f089f292f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:11.538363Z","signature_b64":"PO1Yuose5UFg+MicGn6QS8C0FQzRELe3DvFLiZE1mR9JgOXTyuX0alyPgvg98Togk2WmzMsAOrs7dv6m4jDUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a7a9c8de8f6cf65a0e8e520878018e987ef69b5f01cc8dbc537d1dc8ea76c42","last_reissued_at":"2026-07-05T06:58:11.537917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:11.537917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Frank K. Soong, Lei He, Shaofei Zhang, Sheng Zhao, Tan Lee, Xi Wang, Xu Tan, Yujia Xiao","submitted_at":"2023-07-03T06:55:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00782","kind":"arxiv","version":2},"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/2307.00782/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":"2307.00782","created_at":"2026-07-05T06:58:11.537983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00782v2","created_at":"2026-07-05T06:58:11.537983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00782","created_at":"2026-07-05T06:58:11.537983+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJ5JZDPI63HW","created_at":"2026-07-05T06:58:11.537983+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJ5JZDPI63HWLIHI","created_at":"2026-07-05T06:58:11.537983+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJ5JZDPI","created_at":"2026-07-05T06:58:11.537983+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/BJ5JZDPI63HWLIHI4UQIPAAY5G","json":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G.json","graph_json":"https://pith.science/api/pith-number/BJ5JZDPI63HWLIHI4UQIPAAY5G/graph.json","events_json":"https://pith.science/api/pith-number/BJ5JZDPI63HWLIHI4UQIPAAY5G/events.json","paper":"https://pith.science/paper/BJ5JZDPI"},"agent_actions":{"view_html":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G","download_json":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G.json","view_paper":"https://pith.science/paper/BJ5JZDPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00782&json=true","fetch_graph":"https://pith.science/api/pith-number/BJ5JZDPI63HWLIHI4UQIPAAY5G/graph.json","fetch_events":"https://pith.science/api/pith-number/BJ5JZDPI63HWLIHI4UQIPAAY5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G/action/storage_attestation","attest_author":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G/action/author_attestation","sign_citation":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G/action/citation_signature","submit_replication":"https://pith.science/pith/BJ5JZDPI63HWLIHI4UQIPAAY5G/action/replication_record"}},"created_at":"2026-07-05T06:58:11.537983+00:00","updated_at":"2026-07-05T06:58:11.537983+00:00"}