{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:D6B2KNRJMVO6J4G25CSZLR6VEI","short_pith_number":"pith:D6B2KNRJ","canonical_record":{"source":{"id":"1811.02122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T01:54:22Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"6b867f5212132f62f55412d3dedf8c6ff8e0437ffb9254c2043e684b9b672273","abstract_canon_sha256":"96782a336c82ca6524d892296439727bb884b23561b1f34f1668e59aa5d51510"},"schema_version":"1.0"},"canonical_sha256":"1f83a53629655de4f0dae8a595c7d522114e70ece14476b1b2d05d0e799b25da","source":{"kind":"arxiv","id":"1811.02122","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02122","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02122v2","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02122","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"D6B2KNRJMVO6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D6B2KNRJMVO6J4G2","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D6B2KNRJ","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:D6B2KNRJMVO6J4G25CSZLR6VEI","target":"record","payload":{"canonical_record":{"source":{"id":"1811.02122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T01:54:22Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"6b867f5212132f62f55412d3dedf8c6ff8e0437ffb9254c2043e684b9b672273","abstract_canon_sha256":"96782a336c82ca6524d892296439727bb884b23561b1f34f1668e59aa5d51510"},"schema_version":"1.0"},"canonical_sha256":"1f83a53629655de4f0dae8a595c7d522114e70ece14476b1b2d05d0e799b25da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:50.294766Z","signature_b64":"D54JGY4TpnRWrEXhjZts2NW3sw+phaB3qkJhmG0qF5mCL3vOP38YYCIIBXVcaglcaR4YFiWNulSpIxOMwDz6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f83a53629655de4f0dae8a595c7d522114e70ece14476b1b2d05d0e799b25da","last_reissued_at":"2026-05-17T23:53:50.293995Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:50.293995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.02122","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0JOh7STUvEYuNMvTLx5CYE9XyJ+wFzEcgh02JOmx7NHy4rlyz8VlBF18/Uh7lUwprvTREtBrI4vWHFkdzszVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:55:56.741687Z"},"content_sha256":"073a49ddc8543c61c38aa1b96d42f3426de6103dfb4c9297040ccc99b95dcde1","schema_version":"1.0","event_id":"sha256:073a49ddc8543c61c38aa1b96d42f3426de6103dfb4c9297040ccc99b95dcde1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:D6B2KNRJMVO6J4G25CSZLR6VEI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust and fine-grained prosody control of end-to-end speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Taesu Kim, Younggun Lee","submitted_at":"2018-11-06T01:54:22Z","abstract_excerpt":"We propose prosody embeddings for emotional and expressive speech synthesis networks. The proposed methods introduce temporal structures in the embedding networks, thus enabling fine-grained control of the speaking style of the synthesized speech. The temporal structures can be designed either on the speech side or the text side, leading to different control resolutions in time. The prosody embedding networks are plugged into end-to-end speech synthesis networks and trained without any other supervision except for the target speech for synthesizing. It is demonstrated that the prosody embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02122","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":""},"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":"2026-05-17T23:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKFaHqMsCkOp5JO6uCTREBYCxlCa5/tljAYfwS/qkU8dCtSKoKlbYOgmtbUhqp98aTdz6hLZAdS//b3ahgacAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:55:56.742374Z"},"content_sha256":"9d1db186d9db347ecbc0d96dedfcc365426742928b90d324757bbc68c3f0b8a5","schema_version":"1.0","event_id":"sha256:9d1db186d9db347ecbc0d96dedfcc365426742928b90d324757bbc68c3f0b8a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6B2KNRJMVO6J4G25CSZLR6VEI/bundle.json","state_url":"https://pith.science/pith/D6B2KNRJMVO6J4G25CSZLR6VEI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6B2KNRJMVO6J4G25CSZLR6VEI/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":"2026-05-25T18:55:56Z","links":{"resolver":"https://pith.science/pith/D6B2KNRJMVO6J4G25CSZLR6VEI","bundle":"https://pith.science/pith/D6B2KNRJMVO6J4G25CSZLR6VEI/bundle.json","state":"https://pith.science/pith/D6B2KNRJMVO6J4G25CSZLR6VEI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6B2KNRJMVO6J4G25CSZLR6VEI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:D6B2KNRJMVO6J4G25CSZLR6VEI","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":"96782a336c82ca6524d892296439727bb884b23561b1f34f1668e59aa5d51510","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T01:54:22Z","title_canon_sha256":"6b867f5212132f62f55412d3dedf8c6ff8e0437ffb9254c2043e684b9b672273"},"schema_version":"1.0","source":{"id":"1811.02122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02122","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02122v2","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02122","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"D6B2KNRJMVO6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D6B2KNRJMVO6J4G2","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D6B2KNRJ","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:9d1db186d9db347ecbc0d96dedfcc365426742928b90d324757bbc68c3f0b8a5","target":"graph","created_at":"2026-05-17T23:53:50Z","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"},"paper":{"abstract_excerpt":"We propose prosody embeddings for emotional and expressive speech synthesis networks. The proposed methods introduce temporal structures in the embedding networks, thus enabling fine-grained control of the speaking style of the synthesized speech. The temporal structures can be designed either on the speech side or the text side, leading to different control resolutions in time. The prosody embedding networks are plugged into end-to-end speech synthesis networks and trained without any other supervision except for the target speech for synthesizing. It is demonstrated that the prosody embeddin","authors_text":"Taesu Kim, Younggun Lee","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T01:54:22Z","title":"Robust and fine-grained prosody control of end-to-end speech synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02122","kind":"arxiv","version":2},"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":"sha256:073a49ddc8543c61c38aa1b96d42f3426de6103dfb4c9297040ccc99b95dcde1","target":"record","created_at":"2026-05-17T23:53:50Z","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":"96782a336c82ca6524d892296439727bb884b23561b1f34f1668e59aa5d51510","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T01:54:22Z","title_canon_sha256":"6b867f5212132f62f55412d3dedf8c6ff8e0437ffb9254c2043e684b9b672273"},"schema_version":"1.0","source":{"id":"1811.02122","kind":"arxiv","version":2}},"canonical_sha256":"1f83a53629655de4f0dae8a595c7d522114e70ece14476b1b2d05d0e799b25da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f83a53629655de4f0dae8a595c7d522114e70ece14476b1b2d05d0e799b25da","first_computed_at":"2026-05-17T23:53:50.293995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:50.293995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D54JGY4TpnRWrEXhjZts2NW3sw+phaB3qkJhmG0qF5mCL3vOP38YYCIIBXVcaglcaR4YFiWNulSpIxOMwDz6BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:50.294766Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.02122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:073a49ddc8543c61c38aa1b96d42f3426de6103dfb4c9297040ccc99b95dcde1","sha256:9d1db186d9db347ecbc0d96dedfcc365426742928b90d324757bbc68c3f0b8a5"],"state_sha256":"6140413ced8dc3c92c4da5bbf0b6a70484788c5a81c3b4bb2d7ef7dbe1415bde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Orf7iegy1edkoTvOthVNU4/8SFVFbcJEh05iX93bTM2SKwC83ASEtj9a2WkMrGnTHb6AQAD1xSEIzypDTK2MCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:55:56.745780Z","bundle_sha256":"843f16c6b614c99b6be6d18f6edabe0b1fa4f7f8143af2dc8db6e6056296402a"}}