{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3KHL4XLP445APGEDNMN7MCFHSX","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":"6c5d17ba04e823e84f248e5f3d899416f6348c79848cf60ebdcd513d52175e25","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:21:08Z","title_canon_sha256":"36ff052bd15dc629b9cfd5565fdd264ccee208670f407cfac84bf6b451a4933e"},"schema_version":"1.0","source":{"id":"2203.16930","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16930","created_at":"2026-07-05T05:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16930v2","created_at":"2026-07-05T05:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16930","created_at":"2026-07-05T05:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"3KHL4XLP445A","created_at":"2026-07-05T05:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"3KHL4XLP445APGED","created_at":"2026-07-05T05:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"3KHL4XLP","created_at":"2026-07-05T05:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:598e4e7ebd02f6c03542a3b32339e2f75ea8f300c37a53f00a7426c1c64da40f","target":"graph","created_at":"2026-07-05T05:17:45Z","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/2203.16930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited, because they do not allow to exploit the full potential of a data-driven approach through learning hidden representations. For this reason, several end-to-end methods have been proposed. However, such models are harder to train and require a large number of high-quality recordings with transcriptions. Here, we propose WavThruVec - a two-stage architecture that","authors_text":"Hubert Siuzdak, Nori Jacoby, Piotr Dura, Pol van Rijn","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:21:08Z","title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16930","kind":"arxiv","version":2},"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":"sha256:69c739b373c723a0b529577d5437192efa65e48c79823f1d97d63feb78de9355","target":"record","created_at":"2026-07-05T05:17:45Z","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":"6c5d17ba04e823e84f248e5f3d899416f6348c79848cf60ebdcd513d52175e25","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T10:21:08Z","title_canon_sha256":"36ff052bd15dc629b9cfd5565fdd264ccee208670f407cfac84bf6b451a4933e"},"schema_version":"1.0","source":{"id":"2203.16930","kind":"arxiv","version":2}},"canonical_sha256":"da8ebe5d6fe73a0798836b1bf608a795d5f2498b5eab4611e9cf6207548fed3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da8ebe5d6fe73a0798836b1bf608a795d5f2498b5eab4611e9cf6207548fed3a","first_computed_at":"2026-07-05T05:17:45.433426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:45.433426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zk/5ke1bc5FUKEODvpMh9VtpPbkuxHxJ+AGzzEXm6E3s+AL4BiT+FqHVKdDmEt63dxatx+V8CyhmH+0cUesaAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:45.433836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16930","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69c739b373c723a0b529577d5437192efa65e48c79823f1d97d63feb78de9355","sha256:598e4e7ebd02f6c03542a3b32339e2f75ea8f300c37a53f00a7426c1c64da40f"],"state_sha256":"f9f94b04dbffc77cd8ce497d18bbdcb6b1128e87675444492f44227b00349d14"}