{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XD7LXFU4FKHMVSH47UDKEUSJJD","short_pith_number":"pith:XD7LXFU4","schema_version":"1.0","canonical_sha256":"b8febb969c2a8ecac8fcfd06a2524948fe1a542ab9c6edee72ea80dd34edd89f","source":{"kind":"arxiv","id":"2508.14713","version":1},"attestation_state":"computed","paper":{"title":"Long-Context Speech Synthesis with Context-Aware Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hangrui Hu, Heng Lu, Jingyuan Xing, Xiangmin Xu, Xiaofen Xing, Zhipeng Li","submitted_at":"2025-08-20T13:43:49Z","abstract_excerpt":"In long-text speech synthesis, current approaches typically convert text to speech at the sentence-level and concatenate the results to form pseudo-paragraph-level speech. These methods overlook the contextual coherence of paragraphs, leading to reduced naturalness and inconsistencies in style and timbre across the long-form speech. To address these issues, we propose a Context-Aware Memory (CAM)-based long-context Text-to-Speech (TTS) model. The CAM block integrates and retrieves both long-term memory and local context details, enabling dynamic memory updates and transfers within long paragra"},"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":"2508.14713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-20T13:43:49Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c31ae1beae14947b3eb473f17f8c0632b239804e485348724cdf70d22237163b","abstract_canon_sha256":"c649b1db72137d7ad5c4203bc32574f0dc1aca74bd53c2c8c39022e532a0ee62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:37.322490Z","signature_b64":"Oy9sGCXLXDeBrtS3/1wmiWpPfeUYFxJVbRCtolIhhrQZdscGh6M7tx771nwi0bZvdCyrexcioyl8KnIQwFwADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8febb969c2a8ecac8fcfd06a2524948fe1a542ab9c6edee72ea80dd34edd89f","last_reissued_at":"2026-07-05T11:56:37.321990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:37.321990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Context Speech Synthesis with Context-Aware Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hangrui Hu, Heng Lu, Jingyuan Xing, Xiangmin Xu, Xiaofen Xing, Zhipeng Li","submitted_at":"2025-08-20T13:43:49Z","abstract_excerpt":"In long-text speech synthesis, current approaches typically convert text to speech at the sentence-level and concatenate the results to form pseudo-paragraph-level speech. These methods overlook the contextual coherence of paragraphs, leading to reduced naturalness and inconsistencies in style and timbre across the long-form speech. To address these issues, we propose a Context-Aware Memory (CAM)-based long-context Text-to-Speech (TTS) model. The CAM block integrates and retrieves both long-term memory and local context details, enabling dynamic memory updates and transfers within long paragra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14713","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/2508.14713/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":"2508.14713","created_at":"2026-07-05T11:56:37.322050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14713v1","created_at":"2026-07-05T11:56:37.322050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14713","created_at":"2026-07-05T11:56:37.322050+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD7LXFU4FKHM","created_at":"2026-07-05T11:56:37.322050+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD7LXFU4FKHMVSH4","created_at":"2026-07-05T11:56:37.322050+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD7LXFU4","created_at":"2026-07-05T11:56:37.322050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28618","citing_title":"Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD","json":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD.json","graph_json":"https://pith.science/api/pith-number/XD7LXFU4FKHMVSH47UDKEUSJJD/graph.json","events_json":"https://pith.science/api/pith-number/XD7LXFU4FKHMVSH47UDKEUSJJD/events.json","paper":"https://pith.science/paper/XD7LXFU4"},"agent_actions":{"view_html":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD","download_json":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD.json","view_paper":"https://pith.science/paper/XD7LXFU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14713&json=true","fetch_graph":"https://pith.science/api/pith-number/XD7LXFU4FKHMVSH47UDKEUSJJD/graph.json","fetch_events":"https://pith.science/api/pith-number/XD7LXFU4FKHMVSH47UDKEUSJJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD/action/storage_attestation","attest_author":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD/action/author_attestation","sign_citation":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD/action/citation_signature","submit_replication":"https://pith.science/pith/XD7LXFU4FKHMVSH47UDKEUSJJD/action/replication_record"}},"created_at":"2026-07-05T11:56:37.322050+00:00","updated_at":"2026-07-05T11:56:37.322050+00:00"}