{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NOUDYIPHCDGA2QD3UQRB3JI7YE","short_pith_number":"pith:NOUDYIPH","canonical_record":{"source":{"id":"2304.00714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-04-03T04:21:04Z","cross_cats_sorted":[],"title_canon_sha256":"75216d43250e536f2a5bac61f79951a68843295308fd86c2237da39dffa11e87","abstract_canon_sha256":"d1e27d49cd0d613b469a9b5e794b94f1784210942be142c53eff05e2f61720fa"},"schema_version":"1.0"},"canonical_sha256":"6ba83c21e710cc0d407ba4221da51fc118ab4e2c22bb2074cf9e81093d38933e","source":{"kind":"arxiv","id":"2304.00714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00714","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00714v1","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00714","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"NOUDYIPHCDGA","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"NOUDYIPHCDGA2QD3","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"NOUDYIPH","created_at":"2026-07-05T05:57:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NOUDYIPHCDGA2QD3UQRB3JI7YE","target":"record","payload":{"canonical_record":{"source":{"id":"2304.00714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-04-03T04:21:04Z","cross_cats_sorted":[],"title_canon_sha256":"75216d43250e536f2a5bac61f79951a68843295308fd86c2237da39dffa11e87","abstract_canon_sha256":"d1e27d49cd0d613b469a9b5e794b94f1784210942be142c53eff05e2f61720fa"},"schema_version":"1.0"},"canonical_sha256":"6ba83c21e710cc0d407ba4221da51fc118ab4e2c22bb2074cf9e81093d38933e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:21.295652Z","signature_b64":"ylvHs/qYx7/tgrwGaCygLh2VlZxeaU9AMbBO80akEWkNgR+P39VljGSeSvD7P+LYNj8Nk/pifcuYfD9bvMKcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ba83c21e710cc0d407ba4221da51fc118ab4e2c22bb2074cf9e81093d38933e","last_reissued_at":"2026-07-05T05:57:21.295164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:21.295164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.00714","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":"2026-07-05T05:57:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYjJtJMUO/ZFPr9Pr6D1o4DXtoQjT1r8D9Ag6LlQ1JcvSdirBLIM5ZzdEY7m0gltmJUMRiyY+mSUm0tAnnMWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:29:26.073102Z"},"content_sha256":"c5de8d5139e6214932aff318d1529110b74b70ef7642f9e5e6b8b8b7fe4681bf","schema_version":"1.0","event_id":"sha256:c5de8d5139e6214932aff318d1529110b74b70ef7642f9e5e6b8b8b7fe4681bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NOUDYIPHCDGA2QD3UQRB3JI7YE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensemble prosody prediction for expressive speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alexandra Torresquintero, Christopher G. R. Wallis, Devang S Ram Mohan, James Leoni, Mark Gales, Simon King, Tian Huey Teh, Tom\\'as Gomez Ibarrondo, Vivian Hu, Zack Hodari","submitted_at":"2023-04-03T04:21:04Z","abstract_excerpt":"Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech. Most efforts have focused on sophisticated neural architectures intended to better model the data distribution. Yet, in evaluations it is generally found that no single model is preferred for all input texts. This suggests an approach that has rarely been used before for Text-to-Speech: an ensemble of models. We apply ensemble learning to prosody prediction. We construct simple ensembles of prosody predictors by varying either model architecture or model parameter values. To automatically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00714","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/2304.00714/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":"2026-07-05T05:57:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pEUERo8AqzTxe8QAxyMxSFVSV9s4ZgatX+qlRj8QPqkZNAgUyEUESgohuGSh54esWqurA3YrBWA3w+19P/vJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:29:26.073510Z"},"content_sha256":"d6084de3860fbdce2b2dfee8967d459c2effe3e5d437ddd49c1331263106f255","schema_version":"1.0","event_id":"sha256:d6084de3860fbdce2b2dfee8967d459c2effe3e5d437ddd49c1331263106f255"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOUDYIPHCDGA2QD3UQRB3JI7YE/bundle.json","state_url":"https://pith.science/pith/NOUDYIPHCDGA2QD3UQRB3JI7YE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOUDYIPHCDGA2QD3UQRB3JI7YE/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":"2026-07-06T23:29:26Z","links":{"resolver":"https://pith.science/pith/NOUDYIPHCDGA2QD3UQRB3JI7YE","bundle":"https://pith.science/pith/NOUDYIPHCDGA2QD3UQRB3JI7YE/bundle.json","state":"https://pith.science/pith/NOUDYIPHCDGA2QD3UQRB3JI7YE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOUDYIPHCDGA2QD3UQRB3JI7YE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NOUDYIPHCDGA2QD3UQRB3JI7YE","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":"d1e27d49cd0d613b469a9b5e794b94f1784210942be142c53eff05e2f61720fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-04-03T04:21:04Z","title_canon_sha256":"75216d43250e536f2a5bac61f79951a68843295308fd86c2237da39dffa11e87"},"schema_version":"1.0","source":{"id":"2304.00714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00714","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00714v1","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00714","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"NOUDYIPHCDGA","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"NOUDYIPHCDGA2QD3","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"NOUDYIPH","created_at":"2026-07-05T05:57:21Z"}],"graph_snapshots":[{"event_id":"sha256:d6084de3860fbdce2b2dfee8967d459c2effe3e5d437ddd49c1331263106f255","target":"graph","created_at":"2026-07-05T05:57:21Z","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/2304.00714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech. Most efforts have focused on sophisticated neural architectures intended to better model the data distribution. Yet, in evaluations it is generally found that no single model is preferred for all input texts. This suggests an approach that has rarely been used before for Text-to-Speech: an ensemble of models. We apply ensemble learning to prosody prediction. We construct simple ensembles of prosody predictors by varying either model architecture or model parameter values. To automatically ","authors_text":"Alexandra Torresquintero, Christopher G. R. Wallis, Devang S Ram Mohan, James Leoni, Mark Gales, Simon King, Tian Huey Teh, Tom\\'as Gomez Ibarrondo, Vivian Hu, Zack Hodari","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-04-03T04:21:04Z","title":"Ensemble prosody prediction for expressive speech synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00714","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:c5de8d5139e6214932aff318d1529110b74b70ef7642f9e5e6b8b8b7fe4681bf","target":"record","created_at":"2026-07-05T05:57:21Z","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":"d1e27d49cd0d613b469a9b5e794b94f1784210942be142c53eff05e2f61720fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-04-03T04:21:04Z","title_canon_sha256":"75216d43250e536f2a5bac61f79951a68843295308fd86c2237da39dffa11e87"},"schema_version":"1.0","source":{"id":"2304.00714","kind":"arxiv","version":1}},"canonical_sha256":"6ba83c21e710cc0d407ba4221da51fc118ab4e2c22bb2074cf9e81093d38933e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ba83c21e710cc0d407ba4221da51fc118ab4e2c22bb2074cf9e81093d38933e","first_computed_at":"2026-07-05T05:57:21.295164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:57:21.295164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ylvHs/qYx7/tgrwGaCygLh2VlZxeaU9AMbBO80akEWkNgR+P39VljGSeSvD7P+LYNj8Nk/pifcuYfD9bvMKcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:57:21.295652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5de8d5139e6214932aff318d1529110b74b70ef7642f9e5e6b8b8b7fe4681bf","sha256:d6084de3860fbdce2b2dfee8967d459c2effe3e5d437ddd49c1331263106f255"],"state_sha256":"3f0075493af59a4122976ddf622ae70e10a48ce3f99d0de9b2d41b65d0584e59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vp6mpBCeC2+XyF74Vq9HZyQDvqshqyzLt1lM3Z1SLTjb+PZzhHrpa1VXmrLEGQloIRe5XXfTuVAOSXOROFnqAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:29:26.075506Z","bundle_sha256":"1f781debd682890d84d682fb3c876c228c27261e1d0ef4b6c23ea05456faaf42"}}