{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YPNKDFJLQUPZILAAM7WTIX5OZC","short_pith_number":"pith:YPNKDFJL","schema_version":"1.0","canonical_sha256":"c3daa1952b851f942c0067ed345faec8b4c834436f5a3c3b201d338e35d92430","source":{"kind":"arxiv","id":"1907.02479","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.02479","created_at":"2026-05-17T23:41:28.468043+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02479v1","created_at":"2026-05-17T23:41:28.468043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02479","created_at":"2026-05-17T23:41:28.468043+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPNKDFJLQUPZ","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPNKDFJLQUPZILAA","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPNKDFJL","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC","json":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC.json","graph_json":"https://pith.science/api/pith-number/YPNKDFJLQUPZILAAM7WTIX5OZC/graph.json","events_json":"https://pith.science/api/pith-number/YPNKDFJLQUPZILAAM7WTIX5OZC/events.json","paper":"https://pith.science/paper/YPNKDFJL"},"agent_actions":{"view_html":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC","download_json":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC.json","view_paper":"https://pith.science/paper/YPNKDFJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02479&json=true","fetch_graph":"https://pith.science/api/pith-number/YPNKDFJLQUPZILAAM7WTIX5OZC/graph.json","fetch_events":"https://pith.science/api/pith-number/YPNKDFJLQUPZILAAM7WTIX5OZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/action/storage_attestation","attest_author":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/action/author_attestation","sign_citation":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/action/citation_signature","submit_replication":"https://pith.science/pith/YPNKDFJLQUPZILAAM7WTIX5OZC/action/replication_record"}},"created_at":"2026-05-17T23:41:28.468043+00:00","updated_at":"2026-05-17T23:41:28.468043+00:00"}