{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F7WLGEZ7LTWQ4BC7MDOHFQVXDH","short_pith_number":"pith:F7WLGEZ7","schema_version":"1.0","canonical_sha256":"2fecb3133f5ced0e045f60dc72c2b719f6538c6552d930646f5d6d4323628644","source":{"kind":"arxiv","id":"2108.02271","version":2},"attestation_state":"computed","paper":{"title":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Benjamin van Niekerk, Hugo Seut\\'e, Julian Za\\\"idi, Marc-Andr\\'e Carbonneau","submitted_at":"2021-08-04T20:13:00Z","abstract_excerpt":"This paper presents Daft-Exprt, a multi-speaker acoustic model advancing the state-of-the-art for cross-speaker prosody transfer on any text. This is one of the most challenging, and rarely directly addressed, task in speech synthesis, especially for highly expressive data. Daft-Exprt uses FiLM conditioning layers to strategically inject different prosodic information in all parts of the architecture. The model explicitly encodes traditional low-level prosody features such as pitch, loudness and duration, but also higher level prosodic information that helps generating convincing voices in hig"},"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":"2108.02271","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-08-04T20:13:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"80b80dcc01437983a93332c19a236fd9065872eceb09306d9976175d174cae2f","abstract_canon_sha256":"5350cc6e39c2a648b5a0f85cd2cdd19cf00298876c4b0f05b3e40d379cb0bebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:00.050082Z","signature_b64":"Llm8NIFVwbBJWeItgW/Dt4VFiOEl5toEQSpL9UPSDtMZbU/IfCsKWS5a1wRNeaAZDCwEr+XrGqdkPjWd8ezvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fecb3133f5ced0e045f60dc72c2b719f6538c6552d930646f5d6d4323628644","last_reissued_at":"2026-07-05T06:30:00.049565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:00.049565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Benjamin van Niekerk, Hugo Seut\\'e, Julian Za\\\"idi, Marc-Andr\\'e Carbonneau","submitted_at":"2021-08-04T20:13:00Z","abstract_excerpt":"This paper presents Daft-Exprt, a multi-speaker acoustic model advancing the state-of-the-art for cross-speaker prosody transfer on any text. This is one of the most challenging, and rarely directly addressed, task in speech synthesis, especially for highly expressive data. Daft-Exprt uses FiLM conditioning layers to strategically inject different prosodic information in all parts of the architecture. The model explicitly encodes traditional low-level prosody features such as pitch, loudness and duration, but also higher level prosodic information that helps generating convincing voices in hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02271","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/2108.02271/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":"2108.02271","created_at":"2026-07-05T06:30:00.049624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02271v2","created_at":"2026-07-05T06:30:00.049624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02271","created_at":"2026-07-05T06:30:00.049624+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7WLGEZ7LTWQ","created_at":"2026-07-05T06:30:00.049624+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7WLGEZ7LTWQ4BC7","created_at":"2026-07-05T06:30:00.049624+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7WLGEZ7","created_at":"2026-07-05T06:30:00.049624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14534","citing_title":"Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH","json":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH.json","graph_json":"https://pith.science/api/pith-number/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/graph.json","events_json":"https://pith.science/api/pith-number/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/events.json","paper":"https://pith.science/paper/F7WLGEZ7"},"agent_actions":{"view_html":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH","download_json":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH.json","view_paper":"https://pith.science/paper/F7WLGEZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02271&json=true","fetch_graph":"https://pith.science/api/pith-number/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/graph.json","fetch_events":"https://pith.science/api/pith-number/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/action/storage_attestation","attest_author":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/action/author_attestation","sign_citation":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/action/citation_signature","submit_replication":"https://pith.science/pith/F7WLGEZ7LTWQ4BC7MDOHFQVXDH/action/replication_record"}},"created_at":"2026-07-05T06:30:00.049624+00:00","updated_at":"2026-07-05T06:30:00.049624+00:00"}