{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MYR6G4G3TDL6TBWJQGR3EYFE7G","short_pith_number":"pith:MYR6G4G3","schema_version":"1.0","canonical_sha256":"6623e370db98d7e986c981a3b260a4f9a8ee822ed0c3ca37d4cd87e972fef7b6","source":{"kind":"arxiv","id":"2008.03388","version":2},"attestation_state":"computed","paper":{"title":"Controllable Neural Prosody Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gautham J. Mysore, Justin Salamon, Max Morrison, Nicholas J. Bryan, Zeyu Jin","submitted_at":"2020-08-07T22:11:58Z","abstract_excerpt":"Speech synthesis has recently seen significant improvements in fidelity, driven by the advent of neural vocoders and neural prosody generators. However, these systems lack intuitive user controls over prosody, making them unable to rectify prosody errors (e.g., misplaced emphases and contextually inappropriate emotions) or generate prosodies with diverse speaker excitement levels and emotions. We address these limitations with a user-controllable, context-aware neural prosody generator. Given a real or synthesized speech recording, our model allows a user to input prosody constraints for certa"},"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":"2008.03388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-07T22:11:58Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"6f1eb1e09b79e11e7f214048524d41fc6e3ebaed2d679baa7bdbf4404e3b7feb","abstract_canon_sha256":"16d9127097cbba3b72087ec520cf6703602dc5d1de18a923b9ba02e81a185124"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:31.229393Z","signature_b64":"xAq9SeznVUZAXkFCk+8Pwb1XKCU9Qq+6ckzplGWOVWVmfqmEotWm3juKcO/zw5SzH1w53qjRzuK06MQvOxcbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6623e370db98d7e986c981a3b260a4f9a8ee822ed0c3ca37d4cd87e972fef7b6","last_reissued_at":"2026-07-05T01:26:31.228857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:31.228857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Neural Prosody Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gautham J. Mysore, Justin Salamon, Max Morrison, Nicholas J. Bryan, Zeyu Jin","submitted_at":"2020-08-07T22:11:58Z","abstract_excerpt":"Speech synthesis has recently seen significant improvements in fidelity, driven by the advent of neural vocoders and neural prosody generators. However, these systems lack intuitive user controls over prosody, making them unable to rectify prosody errors (e.g., misplaced emphases and contextually inappropriate emotions) or generate prosodies with diverse speaker excitement levels and emotions. We address these limitations with a user-controllable, context-aware neural prosody generator. Given a real or synthesized speech recording, our model allows a user to input prosody constraints for certa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03388","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.03388/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.03388","created_at":"2026-07-05T01:26:31.228912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03388v2","created_at":"2026-07-05T01:26:31.228912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03388","created_at":"2026-07-05T01:26:31.228912+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYR6G4G3TDL6","created_at":"2026-07-05T01:26:31.228912+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYR6G4G3TDL6TBWJ","created_at":"2026-07-05T01:26:31.228912+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYR6G4G3","created_at":"2026-07-05T01:26:31.228912+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/MYR6G4G3TDL6TBWJQGR3EYFE7G","json":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G.json","graph_json":"https://pith.science/api/pith-number/MYR6G4G3TDL6TBWJQGR3EYFE7G/graph.json","events_json":"https://pith.science/api/pith-number/MYR6G4G3TDL6TBWJQGR3EYFE7G/events.json","paper":"https://pith.science/paper/MYR6G4G3"},"agent_actions":{"view_html":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G","download_json":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G.json","view_paper":"https://pith.science/paper/MYR6G4G3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03388&json=true","fetch_graph":"https://pith.science/api/pith-number/MYR6G4G3TDL6TBWJQGR3EYFE7G/graph.json","fetch_events":"https://pith.science/api/pith-number/MYR6G4G3TDL6TBWJQGR3EYFE7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G/action/storage_attestation","attest_author":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G/action/author_attestation","sign_citation":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G/action/citation_signature","submit_replication":"https://pith.science/pith/MYR6G4G3TDL6TBWJQGR3EYFE7G/action/replication_record"}},"created_at":"2026-07-05T01:26:31.228912+00:00","updated_at":"2026-07-05T01:26:31.228912+00:00"}