{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DFKIMJUFWRUZ6RIMRZSRRJGQ4D","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":"3f07375411444d246e3ecbed2225b0a9666caf979db2768cccb85a720dcd2ef8","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-24T22:15:01Z","title_canon_sha256":"125fb3578dd59226fdc2079ee4a82f48b272a7ce6fe95e4fb9a63b6316c22ae9"},"schema_version":"1.0","source":{"id":"2110.12539","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12539","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12539v3","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12539","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"DFKIMJUFWRUZ","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"pith_short_16","alias_value":"DFKIMJUFWRUZ6RIM","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"pith_short_8","alias_value":"DFKIMJUF","created_at":"2026-07-05T06:50:36Z"}],"graph_snapshots":[{"event_id":"sha256:c3c004c3e9fa9025a8d9b97be398dff515662023cd7cd7f744172f0a27ffcf2b","target":"graph","created_at":"2026-07-05T06:50:36Z","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/2110.12539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a Split Vector Quantized Variational Autoencoder (SVQ-VAE) architecture using a split vector quantizer for NTTS, as an enhancement to the well-known Variational Autoencoder (VAE) and Vector Quantized Variational Autoencoder (VQ-VAE) architectures. Compared to these previous architectures, our proposed model retains the benefits of using an utterance-level bottleneck, while keeping significant representation power and a discretized latent space small enough for efficient prediction from text. We train the model on recordings in the expressive task-oriented dialogues domain and show t","authors_text":"Antonio Bonafonte, Jonas Rohnke, Marek Strong, Mateusz {\\L}ajszczak, Trevor Wood","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-24T22:15:01Z","title":"Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12539","kind":"arxiv","version":3},"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:f175ce1f07b393e9ad9fbfc4f79f252a8710bda3c6cc164d2b658ef130155fe9","target":"record","created_at":"2026-07-05T06:50:36Z","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":"3f07375411444d246e3ecbed2225b0a9666caf979db2768cccb85a720dcd2ef8","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-24T22:15:01Z","title_canon_sha256":"125fb3578dd59226fdc2079ee4a82f48b272a7ce6fe95e4fb9a63b6316c22ae9"},"schema_version":"1.0","source":{"id":"2110.12539","kind":"arxiv","version":3}},"canonical_sha256":"1954862685b4699f450c8e6518a4d0e0cf146ada74b124d3aa8e18c03f3c4eaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1954862685b4699f450c8e6518a4d0e0cf146ada74b124d3aa8e18c03f3c4eaf","first_computed_at":"2026-07-05T06:50:36.301026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:36.301026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Pzqway/cqYeFl/7Ec8vgZ4rA0XNB35ACio2ghPdCtYVdyuQ+D5u8lMoL9faqF6MzAK/sMXEwkYppqQK6eqRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:36.301519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12539","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f175ce1f07b393e9ad9fbfc4f79f252a8710bda3c6cc164d2b658ef130155fe9","sha256:c3c004c3e9fa9025a8d9b97be398dff515662023cd7cd7f744172f0a27ffcf2b"],"state_sha256":"d5d712460e91ddf3f9215413fa01713c086dfa350703d4f7b45115b831e5bd85"}