{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6IZAMT7PKD2W23FWRJNLQJBWXA","short_pith_number":"pith:6IZAMT7P","canonical_record":{"source":{"id":"2209.06484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-14T08:34:16Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"e907f733c420db7ca54ec7a3eb67c037721491e25eabb251438a242c6ebdd6da","abstract_canon_sha256":"d28c435fdabaca11c72286868bcc4122bcc25331fd82ea03cc8f2ee464ea041d"},"schema_version":"1.0"},"canonical_sha256":"f232064fef50f56d6cb68a5ab82436b832b2d6d2685109c8fb0b8bf6d969df18","source":{"kind":"arxiv","id":"2209.06484","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06484","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06484v1","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06484","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"6IZAMT7PKD2W","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"pith_short_16","alias_value":"6IZAMT7PKD2W23FW","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"pith_short_8","alias_value":"6IZAMT7P","created_at":"2026-07-05T04:57:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6IZAMT7PKD2W23FWRJNLQJBWXA","target":"record","payload":{"canonical_record":{"source":{"id":"2209.06484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-14T08:34:16Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"e907f733c420db7ca54ec7a3eb67c037721491e25eabb251438a242c6ebdd6da","abstract_canon_sha256":"d28c435fdabaca11c72286868bcc4122bcc25331fd82ea03cc8f2ee464ea041d"},"schema_version":"1.0"},"canonical_sha256":"f232064fef50f56d6cb68a5ab82436b832b2d6d2685109c8fb0b8bf6d969df18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:31.577097Z","signature_b64":"FDLE4DIxySwsA5Re/27I4+bwLdHkLIE/2k89Xg8EqCS/tDzs5pNiAxjOmAEKkp6EmH6cuGr3vqQyIvUuBAZ3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f232064fef50f56d6cb68a5ab82436b832b2d6d2685109c8fb0b8bf6d969df18","last_reissued_at":"2026-07-05T04:57:31.576708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:31.576708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.06484","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ed/+NFQzxvZabbvLsvQE3QtKOr1EIKzijFhZOkSfzggmTF6DgVQmdTQgUBha4+ZSuYbhKgtwXEGL41fOqDo+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:27:45.651097Z"},"content_sha256":"eb2e8e97fe50db8c4aba316ce5c47989610a53309868f9f40623e2138487e45f","schema_version":"1.0","event_id":"sha256:eb2e8e97fe50db8c4aba316ce5c47989610a53309868f9f40623e2138487e45f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6IZAMT7PKD2W23FWRJNLQJBWXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Frank K. Soong, Lei Xie, Liumeng Xue, Shaofei Zhang","submitted_at":"2022-09-14T08:34:16Z","abstract_excerpt":"Recent advancements in neural end-to-end TTS models have shown high-quality, natural synthesized speech in a conventional sentence-based TTS. However, it is still challenging to reproduce similar high quality when a whole paragraph is considered in TTS, where a large amount of contextual information needs to be considered in building a paragraph-based TTS model. To alleviate the difficulty in training, we propose to model linguistic and prosodic information by considering cross-sentence, embedded structure in training. Three sub-modules, including linguistics-aware, prosody-aware and sentence-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06484","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/2209.06484/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVUqoPSFkjJdECw8buFacX3dm/U9vUKGiPx2QTRNZO/eHjeEcnUaPMGyuryiZVxa2f1YidoklST9Dq2GA519Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:27:45.651747Z"},"content_sha256":"71080f4d0f6546aa4871507bf5b1a9c5f115ea79a7d885923a1704785e441ba8","schema_version":"1.0","event_id":"sha256:71080f4d0f6546aa4871507bf5b1a9c5f115ea79a7d885923a1704785e441ba8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6IZAMT7PKD2W23FWRJNLQJBWXA/bundle.json","state_url":"https://pith.science/pith/6IZAMT7PKD2W23FWRJNLQJBWXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6IZAMT7PKD2W23FWRJNLQJBWXA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T00:27:45Z","links":{"resolver":"https://pith.science/pith/6IZAMT7PKD2W23FWRJNLQJBWXA","bundle":"https://pith.science/pith/6IZAMT7PKD2W23FWRJNLQJBWXA/bundle.json","state":"https://pith.science/pith/6IZAMT7PKD2W23FWRJNLQJBWXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6IZAMT7PKD2W23FWRJNLQJBWXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6IZAMT7PKD2W23FWRJNLQJBWXA","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":"d28c435fdabaca11c72286868bcc4122bcc25331fd82ea03cc8f2ee464ea041d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-14T08:34:16Z","title_canon_sha256":"e907f733c420db7ca54ec7a3eb67c037721491e25eabb251438a242c6ebdd6da"},"schema_version":"1.0","source":{"id":"2209.06484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06484","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06484v1","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06484","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"6IZAMT7PKD2W","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"pith_short_16","alias_value":"6IZAMT7PKD2W23FW","created_at":"2026-07-05T04:57:31Z"},{"alias_kind":"pith_short_8","alias_value":"6IZAMT7P","created_at":"2026-07-05T04:57:31Z"}],"graph_snapshots":[{"event_id":"sha256:71080f4d0f6546aa4871507bf5b1a9c5f115ea79a7d885923a1704785e441ba8","target":"graph","created_at":"2026-07-05T04:57:31Z","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/2209.06484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in neural end-to-end TTS models have shown high-quality, natural synthesized speech in a conventional sentence-based TTS. However, it is still challenging to reproduce similar high quality when a whole paragraph is considered in TTS, where a large amount of contextual information needs to be considered in building a paragraph-based TTS model. To alleviate the difficulty in training, we propose to model linguistic and prosodic information by considering cross-sentence, embedded structure in training. Three sub-modules, including linguistics-aware, prosody-aware and sentence-","authors_text":"Frank K. Soong, Lei Xie, Liumeng Xue, Shaofei Zhang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-14T08:34:16Z","title":"ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06484","kind":"arxiv","version":1},"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:eb2e8e97fe50db8c4aba316ce5c47989610a53309868f9f40623e2138487e45f","target":"record","created_at":"2026-07-05T04:57:31Z","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":"d28c435fdabaca11c72286868bcc4122bcc25331fd82ea03cc8f2ee464ea041d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-14T08:34:16Z","title_canon_sha256":"e907f733c420db7ca54ec7a3eb67c037721491e25eabb251438a242c6ebdd6da"},"schema_version":"1.0","source":{"id":"2209.06484","kind":"arxiv","version":1}},"canonical_sha256":"f232064fef50f56d6cb68a5ab82436b832b2d6d2685109c8fb0b8bf6d969df18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f232064fef50f56d6cb68a5ab82436b832b2d6d2685109c8fb0b8bf6d969df18","first_computed_at":"2026-07-05T04:57:31.576708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:31.576708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FDLE4DIxySwsA5Re/27I4+bwLdHkLIE/2k89Xg8EqCS/tDzs5pNiAxjOmAEKkp6EmH6cuGr3vqQyIvUuBAZ3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:31.577097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb2e8e97fe50db8c4aba316ce5c47989610a53309868f9f40623e2138487e45f","sha256:71080f4d0f6546aa4871507bf5b1a9c5f115ea79a7d885923a1704785e441ba8"],"state_sha256":"1230c3266e80994c372315a2ef2ab96e74d13fd226cc8f41c5fd644d0eab0c23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3YfaOQkrAf6+gCqzgH+2Weo5KA8TIHYhB2ldQiBpFxDhqVL8OZbkTapApQ0gK65d6JkmWuJE2oGBQfFgc52AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:27:45.657774Z","bundle_sha256":"ff88e987a75c7e52f122c834b8b32397a04131b70bb88c3001d795af82fe854f"}}