{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J37XYQD3RYMW7DPE5UFCK5ACVJ","short_pith_number":"pith:J37XYQD3","schema_version":"1.0","canonical_sha256":"4eff7c407b8e196f8de4ed0a257402aa4e29b1b18bc81fce193401fdd72fa183","source":{"kind":"arxiv","id":"2303.09446","version":2},"attestation_state":"computed","paper":{"title":"Controllable Prosody Generation With Partial Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Dan Andrei Iliescu, Devang Savita Ram Mohan, Tian Huey Teh, Zack Hodari","submitted_at":"2023-03-14T09:47:23Z","abstract_excerpt":"We address the problem of human-in-the-loop control for generating prosody in the context of text-to-speech synthesis. Controlling prosody is challenging because existing generative models lack an efficient interface through which users can modify the output quickly and precisely. To solve this, we introduce a novel framework whereby the user provides partial inputs and the generative model generates the missing features. We propose a model that is specifically designed to encode partial prosodic features and output complete audio. We show empirically that our model displays two essential qual"},"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":"2303.09446","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-14T09:47:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"1a17a849a97df3382847dd5402eba933afde9d5edd7175a752721714f32d5eed","abstract_canon_sha256":"dfc9359670a9b77aa5f71c5de858697ce81308f19376299ad56c5bb4e6062eee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:16.229555Z","signature_b64":"/gCxDOwWEFTdCMWK7XxWEGMU1LTmTZGkn1GUu8h3eVXxyYgioMJ+/VqJwCsIZjjBLxQLRSLyJ/NE0phbLSncAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eff7c407b8e196f8de4ed0a257402aa4e29b1b18bc81fce193401fdd72fa183","last_reissued_at":"2026-07-05T08:08:16.229140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:16.229140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Prosody Generation With Partial Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Dan Andrei Iliescu, Devang Savita Ram Mohan, Tian Huey Teh, Zack Hodari","submitted_at":"2023-03-14T09:47:23Z","abstract_excerpt":"We address the problem of human-in-the-loop control for generating prosody in the context of text-to-speech synthesis. Controlling prosody is challenging because existing generative models lack an efficient interface through which users can modify the output quickly and precisely. To solve this, we introduce a novel framework whereby the user provides partial inputs and the generative model generates the missing features. We propose a model that is specifically designed to encode partial prosodic features and output complete audio. We show empirically that our model displays two essential qual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09446","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/2303.09446/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":"2303.09446","created_at":"2026-07-05T08:08:16.229204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09446v2","created_at":"2026-07-05T08:08:16.229204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09446","created_at":"2026-07-05T08:08:16.229204+00:00"},{"alias_kind":"pith_short_12","alias_value":"J37XYQD3RYMW","created_at":"2026-07-05T08:08:16.229204+00:00"},{"alias_kind":"pith_short_16","alias_value":"J37XYQD3RYMW7DPE","created_at":"2026-07-05T08:08:16.229204+00:00"},{"alias_kind":"pith_short_8","alias_value":"J37XYQD3","created_at":"2026-07-05T08:08:16.229204+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/J37XYQD3RYMW7DPE5UFCK5ACVJ","json":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ.json","graph_json":"https://pith.science/api/pith-number/J37XYQD3RYMW7DPE5UFCK5ACVJ/graph.json","events_json":"https://pith.science/api/pith-number/J37XYQD3RYMW7DPE5UFCK5ACVJ/events.json","paper":"https://pith.science/paper/J37XYQD3"},"agent_actions":{"view_html":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ","download_json":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ.json","view_paper":"https://pith.science/paper/J37XYQD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09446&json=true","fetch_graph":"https://pith.science/api/pith-number/J37XYQD3RYMW7DPE5UFCK5ACVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/J37XYQD3RYMW7DPE5UFCK5ACVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ/action/storage_attestation","attest_author":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ/action/author_attestation","sign_citation":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ/action/citation_signature","submit_replication":"https://pith.science/pith/J37XYQD3RYMW7DPE5UFCK5ACVJ/action/replication_record"}},"created_at":"2026-07-05T08:08:16.229204+00:00","updated_at":"2026-07-05T08:08:16.229204+00:00"}