{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EULHK5Z3R5W4UYRA22V5LT774N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dc814caf0b1806b62fbc4dadaa7c64129a604011d1a6d8982a47ad3b7bdebb4b","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-20T06:50:52Z","title_canon_sha256":"e6ff88859eeb7dc679af490a840a032a0c04db3b4134c1bf529ae9f62e9df1de"},"schema_version":"1.0","source":{"id":"2306.11327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11327","created_at":"2026-07-05T06:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11327v1","created_at":"2026-07-05T06:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11327","created_at":"2026-07-05T06:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"EULHK5Z3R5W4","created_at":"2026-07-05T06:22:18Z"},{"alias_kind":"pith_short_16","alias_value":"EULHK5Z3R5W4UYRA","created_at":"2026-07-05T06:22:18Z"},{"alias_kind":"pith_short_8","alias_value":"EULHK5Z3","created_at":"2026-07-05T06:22:18Z"}],"graph_snapshots":[{"event_id":"sha256:a021f6f517b8096a69f926b0be4f41bba3d87eed706e7eebd8f5a56cf825d893","target":"graph","created_at":"2026-07-05T06:22:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.11327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present eCat, a novel end-to-end multispeaker model capable of: a) generating long-context speech with expressive and contextually appropriate prosody, and b) performing fine-grained prosody transfer between any pair of seen speakers. eCat is trained using a two-stage training approach. In Stage I, the model learns speaker-independent word-level prosody representations in an end-to-end fashion from speech. In Stage II, we learn to predict the prosody representations using the contextual information available in text. We compare eCat to CopyCat2, a model capable of both fine-grained prosody ","authors_text":"Alexis Moinet, Amith Nagaraj, Ammar Abbas, Ayman Boustati, Bastian Schnell, Marcel Granero Moya, Nicole Peinelt, Penny Karanasou, Sri Karlapati, Thomas Drugman","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-20T06:50:52Z","title":"eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11327","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7bb42d515bc25c795f086ae9c9c056e266c1ceb849ab80b60f5b71ae4a4744d3","target":"record","created_at":"2026-07-05T06:22:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dc814caf0b1806b62fbc4dadaa7c64129a604011d1a6d8982a47ad3b7bdebb4b","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-20T06:50:52Z","title_canon_sha256":"e6ff88859eeb7dc679af490a840a032a0c04db3b4134c1bf529ae9f62e9df1de"},"schema_version":"1.0","source":{"id":"2306.11327","kind":"arxiv","version":1}},"canonical_sha256":"251675773b8f6dca6220d6abd5cfffe341d02b632727e445d94ea8881af61056","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"251675773b8f6dca6220d6abd5cfffe341d02b632727e445d94ea8881af61056","first_computed_at":"2026-07-05T06:22:18.491940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:22:18.491940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9uNU00wyNTWU8dkukJW+Oocbyoj4Av53q9zq7GEB8tBE5lQ+JG4+XGHtE0sIuFxuKGv2JW+X60RJcliQvXFQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:22:18.492401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bb42d515bc25c795f086ae9c9c056e266c1ceb849ab80b60f5b71ae4a4744d3","sha256:a021f6f517b8096a69f926b0be4f41bba3d87eed706e7eebd8f5a56cf825d893"],"state_sha256":"353198002f6de1d06f20ba77fc4ddcb075e07ba7f5f275929750b2c6d8b31f42"}