{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TVHJ4PFOT6XJ4OYIGZCGGR4T4F","short_pith_number":"pith:TVHJ4PFO","schema_version":"1.0","canonical_sha256":"9d4e9e3cae9fae9e3b083644634793e16b81f9b62d9d56ea2689d3c88d42c10b","source":{"kind":"arxiv","id":"2110.06306","version":2},"attestation_state":"computed","paper":{"title":"Fine-grained style control in Transformer-based Text-to-speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Rudnicky, Li-Wei Chen","submitted_at":"2021-10-12T19:50:02Z","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"},"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":"2110.06306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-12T19:50:02Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"70a2effb204d3bfefd8d2b84ab6461df43d4f799a72180d2644268826e94ed90","abstract_canon_sha256":"08195745b0abdff6f2c5545e23e1d6fbed4940244abacd3f9d50fb6577461c7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:00.050377Z","signature_b64":"off1OxVXFQmnutlCQvm3jL7jgiBCpcVZflBMPeRONy0VE7/WnzW369ZkBIohAJfFyD2VwmM4kavG9z1YGiG5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d4e9e3cae9fae9e3b083644634793e16b81f9b62d9d56ea2689d3c88d42c10b","last_reissued_at":"2026-07-05T04:06:00.050020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:00.050020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-grained style control in Transformer-based Text-to-speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Rudnicky, Li-Wei Chen","submitted_at":"2021-10-12T19:50:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06306","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/2110.06306/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":"2110.06306","created_at":"2026-07-05T04:06:00.050081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06306v2","created_at":"2026-07-05T04:06:00.050081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06306","created_at":"2026-07-05T04:06:00.050081+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVHJ4PFOT6XJ","created_at":"2026-07-05T04:06:00.050081+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVHJ4PFOT6XJ4OYI","created_at":"2026-07-05T04:06:00.050081+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVHJ4PFO","created_at":"2026-07-05T04:06:00.050081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F","json":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F.json","graph_json":"https://pith.science/api/pith-number/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/graph.json","events_json":"https://pith.science/api/pith-number/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/events.json","paper":"https://pith.science/paper/TVHJ4PFO"},"agent_actions":{"view_html":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F","download_json":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F.json","view_paper":"https://pith.science/paper/TVHJ4PFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06306&json=true","fetch_graph":"https://pith.science/api/pith-number/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/graph.json","fetch_events":"https://pith.science/api/pith-number/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/action/storage_attestation","attest_author":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/action/author_attestation","sign_citation":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/action/citation_signature","submit_replication":"https://pith.science/pith/TVHJ4PFOT6XJ4OYIGZCGGR4T4F/action/replication_record"}},"created_at":"2026-07-05T04:06:00.050081+00:00","updated_at":"2026-07-05T04:06:00.050081+00:00"}