{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XWE2U5Y46YJTVEQN4VXFKMBSZI","short_pith_number":"pith:XWE2U5Y4","canonical_record":{"source":{"id":"2308.13365","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-25T13:22:42Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"45f95bcfa77962354f618353c2bbe7f88f0a12a8e35756dbca9b4221980f6328","abstract_canon_sha256":"31a9129c16a0d79aa0286eebc439b79bf11ebae7c3b74f509e42dca5d3e2800c"},"schema_version":"1.0"},"canonical_sha256":"bd89aa771cf6133a920de56e553032ca206acc6e1b224874d3094fc4b5e8446a","source":{"kind":"arxiv","id":"2308.13365","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13365","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13365v4","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13365","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"XWE2U5Y46YJT","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"XWE2U5Y46YJTVEQN","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"XWE2U5Y4","created_at":"2026-07-05T09:11:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XWE2U5Y46YJTVEQN4VXFKMBSZI","target":"record","payload":{"canonical_record":{"source":{"id":"2308.13365","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-25T13:22:42Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"45f95bcfa77962354f618353c2bbe7f88f0a12a8e35756dbca9b4221980f6328","abstract_canon_sha256":"31a9129c16a0d79aa0286eebc439b79bf11ebae7c3b74f509e42dca5d3e2800c"},"schema_version":"1.0"},"canonical_sha256":"bd89aa771cf6133a920de56e553032ca206acc6e1b224874d3094fc4b5e8446a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:21.922090Z","signature_b64":"TcAcXaNqd/iWia6p0OOofNh9tS1hxvAcF5yMg+GPko1Y+Dgac1l34LhMHS7NeZKs3jqqXXwPZqwBQbjtZohJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd89aa771cf6133a920de56e553032ca206acc6e1b224874d3094fc4b5e8446a","last_reissued_at":"2026-07-05T09:11:21.921625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:21.921625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.13365","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:11:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwVE7HYdJHA/1HjFdC2bVspvjEg7Xq3E5nTqVTmKHWDvii3xCFjcOm8X4mtQh/x3FDEhFQMpe5edMRuhgBShBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T21:06:45.775842Z"},"content_sha256":"08e1e52ef27351107fa8cbb095a316162e4b954315310f2c1bf5a71fc8e11de6","schema_version":"1.0","event_id":"sha256:08e1e52ef27351107fa8cbb095a316162e4b954315310f2c1bf5a71fc8e11de6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XWE2U5Y46YJTVEQN4VXFKMBSZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expressive paragraph text-to-speech synthesis with multi-step variational autoencoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hua Hua, Peiyang Shi, Pengyuan Zhang, Ta Li, Xuyuan Li, Zengqiang Shang","submitted_at":"2023-08-25T13:22:42Z","abstract_excerpt":"Neural networks have been able to generate high-quality single-sentence speech. However, it remains a challenge concerning audio-book speech synthesis due to the intra-paragraph correlation of semantic and acoustic features as well as variable styles. In this paper, we propose a highly expressive paragraph speech synthesis system with a multi-step variational autoencoder, called EP-MSTTS. EP-MSTTS is the first VITS-based paragraph speech synthesis model and models the variable style of paragraph speech at five levels: frame, phoneme, word, sentence, and paragraph. We also propose a series of i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13365","kind":"arxiv","version":4},"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/2308.13365/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":"2026-07-05T09:11:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TIPoPv0LIZ/UN08eXc2t0P0MUBBAbjs+3JO05JkAbNsAfUuGIEnEH8WchhVXpYxevSbyVRtntcVqIcZHvOvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T21:06:45.776346Z"},"content_sha256":"89583f3c05880f0939d9de2ed7e82b7ef66136b2dffc6207b3cc43dfaadf3d46","schema_version":"1.0","event_id":"sha256:89583f3c05880f0939d9de2ed7e82b7ef66136b2dffc6207b3cc43dfaadf3d46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWE2U5Y46YJTVEQN4VXFKMBSZI/bundle.json","state_url":"https://pith.science/pith/XWE2U5Y46YJTVEQN4VXFKMBSZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWE2U5Y46YJTVEQN4VXFKMBSZI/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":"2026-08-22T21:06:45Z","links":{"resolver":"https://pith.science/pith/XWE2U5Y46YJTVEQN4VXFKMBSZI","bundle":"https://pith.science/pith/XWE2U5Y46YJTVEQN4VXFKMBSZI/bundle.json","state":"https://pith.science/pith/XWE2U5Y46YJTVEQN4VXFKMBSZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWE2U5Y46YJTVEQN4VXFKMBSZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XWE2U5Y46YJTVEQN4VXFKMBSZI","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":"31a9129c16a0d79aa0286eebc439b79bf11ebae7c3b74f509e42dca5d3e2800c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-25T13:22:42Z","title_canon_sha256":"45f95bcfa77962354f618353c2bbe7f88f0a12a8e35756dbca9b4221980f6328"},"schema_version":"1.0","source":{"id":"2308.13365","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13365","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13365v4","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13365","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"XWE2U5Y46YJT","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"XWE2U5Y46YJTVEQN","created_at":"2026-07-05T09:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"XWE2U5Y4","created_at":"2026-07-05T09:11:21Z"}],"graph_snapshots":[{"event_id":"sha256:89583f3c05880f0939d9de2ed7e82b7ef66136b2dffc6207b3cc43dfaadf3d46","target":"graph","created_at":"2026-07-05T09:11:21Z","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/2308.13365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks have been able to generate high-quality single-sentence speech. However, it remains a challenge concerning audio-book speech synthesis due to the intra-paragraph correlation of semantic and acoustic features as well as variable styles. In this paper, we propose a highly expressive paragraph speech synthesis system with a multi-step variational autoencoder, called EP-MSTTS. EP-MSTTS is the first VITS-based paragraph speech synthesis model and models the variable style of paragraph speech at five levels: frame, phoneme, word, sentence, and paragraph. We also propose a series of i","authors_text":"Hua Hua, Peiyang Shi, Pengyuan Zhang, Ta Li, Xuyuan Li, Zengqiang Shang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-25T13:22:42Z","title":"Expressive paragraph text-to-speech synthesis with multi-step variational autoencoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13365","kind":"arxiv","version":4},"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":"sha256:08e1e52ef27351107fa8cbb095a316162e4b954315310f2c1bf5a71fc8e11de6","target":"record","created_at":"2026-07-05T09:11:21Z","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":"31a9129c16a0d79aa0286eebc439b79bf11ebae7c3b74f509e42dca5d3e2800c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-25T13:22:42Z","title_canon_sha256":"45f95bcfa77962354f618353c2bbe7f88f0a12a8e35756dbca9b4221980f6328"},"schema_version":"1.0","source":{"id":"2308.13365","kind":"arxiv","version":4}},"canonical_sha256":"bd89aa771cf6133a920de56e553032ca206acc6e1b224874d3094fc4b5e8446a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd89aa771cf6133a920de56e553032ca206acc6e1b224874d3094fc4b5e8446a","first_computed_at":"2026-07-05T09:11:21.921625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:21.921625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TcAcXaNqd/iWia6p0OOofNh9tS1hxvAcF5yMg+GPko1Y+Dgac1l34LhMHS7NeZKs3jqqXXwPZqwBQbjtZohJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:21.922090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13365","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08e1e52ef27351107fa8cbb095a316162e4b954315310f2c1bf5a71fc8e11de6","sha256:89583f3c05880f0939d9de2ed7e82b7ef66136b2dffc6207b3cc43dfaadf3d46"],"state_sha256":"eac315e4f049945178706f645326e0cb3e918f8fad22e9315aa9c8103fd1bf36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8vWLaa17ho1oo/qwWQTij8rgIH/qzKleQNiLys9v1YwmhmpRfd9U6l3iAc4gtF15gUaOeahdeWIQII5gl82Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T21:06:45.782102Z","bundle_sha256":"32c42f2231105421528c436a60b573ad3e04ac5bda78b593e58e0167db3b22e8"}}