{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TVHJ4PFOT6XJ4OYIGZCGGR4T4F","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":"08195745b0abdff6f2c5545e23e1d6fbed4940244abacd3f9d50fb6577461c7c","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-12T19:50:02Z","title_canon_sha256":"70a2effb204d3bfefd8d2b84ab6461df43d4f799a72180d2644268826e94ed90"},"schema_version":"1.0","source":{"id":"2110.06306","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06306","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06306v2","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06306","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"TVHJ4PFOT6XJ","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"TVHJ4PFOT6XJ4OYI","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"TVHJ4PFO","created_at":"2026-07-05T04:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:bdb714630adb4a375dc033b87ac5dee9609b8bec2e2de0a003febec04e8b5243","target":"graph","created_at":"2026-07-05T04:06:00Z","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/2110.06306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a novel architecture to realize fine-grained style control on the transformer-based text-to-speech synthesis (TransformerTTS). Specifically, we model the speaking style by extracting a time sequence of local style tokens (LST) from the reference speech. The existing content encoder in TransformerTTS is then replaced by our designed cross-attention blocks for fusion and alignment between content and style. As the fusion is performed along with the skip connection, our cross-attention block provides a good inductive bias to gradually infuse the phoneme representation wi","authors_text":"Alexander Rudnicky, Li-Wei Chen","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-12T19:50:02Z","title":"Fine-grained style control in Transformer-based Text-to-speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06306","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":"sha256:4c6e0072d716a659ac3dae696d03025aaa307d206e2bc5b8317c690f249bd028","target":"record","created_at":"2026-07-05T04:06:00Z","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":"08195745b0abdff6f2c5545e23e1d6fbed4940244abacd3f9d50fb6577461c7c","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-12T19:50:02Z","title_canon_sha256":"70a2effb204d3bfefd8d2b84ab6461df43d4f799a72180d2644268826e94ed90"},"schema_version":"1.0","source":{"id":"2110.06306","kind":"arxiv","version":2}},"canonical_sha256":"9d4e9e3cae9fae9e3b083644634793e16b81f9b62d9d56ea2689d3c88d42c10b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d4e9e3cae9fae9e3b083644634793e16b81f9b62d9d56ea2689d3c88d42c10b","first_computed_at":"2026-07-05T04:06:00.050020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:00.050020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"off1OxVXFQmnutlCQvm3jL7jgiBCpcVZflBMPeRONy0VE7/WnzW369ZkBIohAJfFyD2VwmM4kavG9z1YGiG5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:00.050377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06306","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c6e0072d716a659ac3dae696d03025aaa307d206e2bc5b8317c690f249bd028","sha256:bdb714630adb4a375dc033b87ac5dee9609b8bec2e2de0a003febec04e8b5243"],"state_sha256":"16b338c4952dffd06e41451392e07f403d84c4fff97c52f34d5b076c6f9f36ab"}