{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YPNKDFJLQUPZILAAM7WTIX5OZC","short_pith_number":"pith:YPNKDFJL","canonical_record":{"source":{"id":"1907.02479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-07-04T16:20:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"17973ef9b0442daf8ff9dce413971a40a4470e844f4c115e2b93686af3e58bf6","abstract_canon_sha256":"5ce1c3c7bc0daa3ad63d1bee9001d1a1dbd77519251df90a9aefbaa2f03d8247"},"schema_version":"1.0"},"canonical_sha256":"c3daa1952b851f942c0067ed345faec8b4c834436f5a3c3b201d338e35d92430","source":{"kind":"arxiv","id":"1907.02479","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02479","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02479v1","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02479","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"YPNKDFJLQUPZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YPNKDFJLQUPZILAA","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YPNKDFJL","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YPNKDFJLQUPZILAAM7WTIX5OZC","target":"record","payload":{"canonical_record":{"source":{"id":"1907.02479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-07-04T16:20:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"17973ef9b0442daf8ff9dce413971a40a4470e844f4c115e2b93686af3e58bf6","abstract_canon_sha256":"5ce1c3c7bc0daa3ad63d1bee9001d1a1dbd77519251df90a9aefbaa2f03d8247"},"schema_version":"1.0"},"canonical_sha256":"c3daa1952b851f942c0067ed345faec8b4c834436f5a3c3b201d338e35d92430","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:28.468668Z","signature_b64":"Gq5G2CYODBi55eLsdfiYmrOtiCBj1X/1blycDQpvKXVx6AOIeGeOdG+d20RCViNGJGyntIP4SXDxQ+NxrGDHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3daa1952b851f942c0067ed345faec8b4c834436f5a3c3b201d338e35d92430","last_reissued_at":"2026-05-17T23:41:28.467930Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:28.467930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.02479","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":"2026-05-17T23:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pshUWMNGCaYJwqIUctHbpn31C+7icRE/e4HCmJW/5E6lS8YKusmM+KlHxYZx/pUvNzjomzjtHX/p0zqsLRMaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:01:51.189043Z"},"content_sha256":"dd906e03dd8b904070db856a5436b4ce9797ff0abd5c65cf8406da2350c89789","schema_version":"1.0","event_id":"sha256:dd906e03dd8b904070db856a5436b4ce9797ff0abd5c65cf8406da2350c89789"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YPNKDFJLQUPZILAAM7WTIX5OZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-grained robust prosody transfer for single-speaker neural text-to-speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Jonas Rohnke, Srikanth Ronanki, Thomas Drugman, Viacheslav Klimkov","submitted_at":"2019-07-04T16:20:42Z","abstract_excerpt":"We present a neural text-to-speech system for fine-grained prosody transfer from one speaker to another. Conventional approaches for end-to-end prosody transfer typically use either fixed-dimensional or variable-length prosody embedding via a secondary attention to encode the reference signal. However, when trained on a single-speaker dataset, the conventional prosody transfer systems are not robust enough to speaker variability, especially in the case of a reference signal coming from an unseen speaker. Therefore, we propose decoupling of the reference signal alignment from the overall system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02479","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":""},"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":"2026-05-17T23:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLpqsXms7jTKc+cfXdXvwWluo7MqAZ8qpf2Pc/XBO8DUDaQqzzLg6xOXCVbPVr1RiY7sbPCPI7dewKhaWb0fAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:01:51.189755Z"},"content_sha256":"b65b0057690490ae435751b8ecfe55eef1f12986c26d774947b569f110954431","schema_version":"1.0","event_id":"sha256:b65b0057690490ae435751b8ecfe55eef1f12986c26d774947b569f110954431"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/bundle.json","state_url":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/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":"2026-05-24T06:01:51Z","links":{"resolver":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC","bundle":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/bundle.json","state":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YPNKDFJLQUPZILAAM7WTIX5OZC","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":"5ce1c3c7bc0daa3ad63d1bee9001d1a1dbd77519251df90a9aefbaa2f03d8247","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-07-04T16:20:42Z","title_canon_sha256":"17973ef9b0442daf8ff9dce413971a40a4470e844f4c115e2b93686af3e58bf6"},"schema_version":"1.0","source":{"id":"1907.02479","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02479","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02479v1","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02479","created_at":"2026-05-17T23:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"YPNKDFJLQUPZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YPNKDFJLQUPZILAA","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YPNKDFJL","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:b65b0057690490ae435751b8ecfe55eef1f12986c26d774947b569f110954431","target":"graph","created_at":"2026-05-17T23:41:28Z","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 present a neural text-to-speech system for fine-grained prosody transfer from one speaker to another. Conventional approaches for end-to-end prosody transfer typically use either fixed-dimensional or variable-length prosody embedding via a secondary attention to encode the reference signal. However, when trained on a single-speaker dataset, the conventional prosody transfer systems are not robust enough to speaker variability, especially in the case of a reference signal coming from an unseen speaker. Therefore, we propose decoupling of the reference signal alignment from the overall system","authors_text":"Jonas Rohnke, Srikanth Ronanki, Thomas Drugman, Viacheslav Klimkov","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-07-04T16:20:42Z","title":"Fine-grained robust prosody transfer for single-speaker neural text-to-speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02479","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:dd906e03dd8b904070db856a5436b4ce9797ff0abd5c65cf8406da2350c89789","target":"record","created_at":"2026-05-17T23:41:28Z","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":"5ce1c3c7bc0daa3ad63d1bee9001d1a1dbd77519251df90a9aefbaa2f03d8247","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-07-04T16:20:42Z","title_canon_sha256":"17973ef9b0442daf8ff9dce413971a40a4470e844f4c115e2b93686af3e58bf6"},"schema_version":"1.0","source":{"id":"1907.02479","kind":"arxiv","version":1}},"canonical_sha256":"c3daa1952b851f942c0067ed345faec8b4c834436f5a3c3b201d338e35d92430","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3daa1952b851f942c0067ed345faec8b4c834436f5a3c3b201d338e35d92430","first_computed_at":"2026-05-17T23:41:28.467930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:28.467930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gq5G2CYODBi55eLsdfiYmrOtiCBj1X/1blycDQpvKXVx6AOIeGeOdG+d20RCViNGJGyntIP4SXDxQ+NxrGDHCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:28.468668Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.02479","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd906e03dd8b904070db856a5436b4ce9797ff0abd5c65cf8406da2350c89789","sha256:b65b0057690490ae435751b8ecfe55eef1f12986c26d774947b569f110954431"],"state_sha256":"e9abafca32785e6e2a57959837027bbd8727317a69e3ae8164d5485a7d2108d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCR0z24TdHKlVspoGo11W7QwNGUCMlevnOGsufBsWqdqYuOaaYvY/EoP3mw8Zhwq6j8zkCdvIRQmKCXLGlpLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T06:01:51.193666Z","bundle_sha256":"c98ffe2d7f94a3d8d60eeaa86e6e0a97ee2d85653f22ee8ab00e90925024f125"}}