{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OQUD6ZQBI5LK5W2AFCR6M7VPWI","short_pith_number":"pith:OQUD6ZQB","schema_version":"1.0","canonical_sha256":"74283f66014756aedb4028a3e67eafb23aa081a1c0f7f00cebe37f26ab1371e3","source":{"kind":"arxiv","id":"2010.15084","version":1},"attestation_state":"computed","paper":{"title":"Speech Synthesis and Control Using Differentiable DSP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Cremers, Giorgio Fabbro, Thomas Kemp, Vladimir Golkov","submitted_at":"2020-10-28T16:55:38Z","abstract_excerpt":"Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\\ that text alone cannot contain. In this work we move towards a speech synthesis system that can produce diverse speech renditions of a text by allowing (but not requiring) explicit control over the various factors of variation. We propose a new neural vocoder that offers control of such factors of variation. This is achieved by employing differentiable digital signal processing (DDSP) (previously used only for music rather than spee"},"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":"2010.15084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-28T16:55:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"bce216b3c223cd552caf79e060a2c578fe45d03c2b27a303cdc8d074ed6c15a1","abstract_canon_sha256":"9940a81ffe8a64acceadef457b3275fbc0feb31f56363aa7c56b2bde59cae7e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:27.597466Z","signature_b64":"MBe6lMZda3CmExtdq8N8MrVvVliIdauJAfTm3ZAPSqRTIwmqLuZZqgb2IioaQWlgqObpivvG24NGJAGym1WUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74283f66014756aedb4028a3e67eafb23aa081a1c0f7f00cebe37f26ab1371e3","last_reissued_at":"2026-07-05T01:47:27.597075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:27.597075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Synthesis and Control Using Differentiable DSP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Cremers, Giorgio Fabbro, Thomas Kemp, Vladimir Golkov","submitted_at":"2020-10-28T16:55:38Z","abstract_excerpt":"Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\\ that text alone cannot contain. In this work we move towards a speech synthesis system that can produce diverse speech renditions of a text by allowing (but not requiring) explicit control over the various factors of variation. We propose a new neural vocoder that offers control of such factors of variation. This is achieved by employing differentiable digital signal processing (DDSP) (previously used only for music rather than spee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15084","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.15084/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":"2010.15084","created_at":"2026-07-05T01:47:27.597136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.15084v1","created_at":"2026-07-05T01:47:27.597136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15084","created_at":"2026-07-05T01:47:27.597136+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQUD6ZQBI5LK","created_at":"2026-07-05T01:47:27.597136+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQUD6ZQBI5LK5W2A","created_at":"2026-07-05T01:47:27.597136+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQUD6ZQB","created_at":"2026-07-05T01:47:27.597136+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/OQUD6ZQBI5LK5W2AFCR6M7VPWI","json":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI.json","graph_json":"https://pith.science/api/pith-number/OQUD6ZQBI5LK5W2AFCR6M7VPWI/graph.json","events_json":"https://pith.science/api/pith-number/OQUD6ZQBI5LK5W2AFCR6M7VPWI/events.json","paper":"https://pith.science/paper/OQUD6ZQB"},"agent_actions":{"view_html":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI","download_json":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI.json","view_paper":"https://pith.science/paper/OQUD6ZQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.15084&json=true","fetch_graph":"https://pith.science/api/pith-number/OQUD6ZQBI5LK5W2AFCR6M7VPWI/graph.json","fetch_events":"https://pith.science/api/pith-number/OQUD6ZQBI5LK5W2AFCR6M7VPWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI/action/storage_attestation","attest_author":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI/action/author_attestation","sign_citation":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI/action/citation_signature","submit_replication":"https://pith.science/pith/OQUD6ZQBI5LK5W2AFCR6M7VPWI/action/replication_record"}},"created_at":"2026-07-05T01:47:27.597136+00:00","updated_at":"2026-07-05T01:47:27.597136+00:00"}