{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NU6JYNQO4BTR5MPCACKXNWQBUV","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":"c8119028b74b43fe46b5c68033984842baf4360eb1960a4645e0e09ab00aecf2","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-08T05:50:09Z","title_canon_sha256":"a0a7f0420bac60855f784a601bdd92e5f986348917294c89d309a1033f7e1400"},"schema_version":"1.0","source":{"id":"2104.03521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03521","created_at":"2026-07-05T02:30:18Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03521v1","created_at":"2026-07-05T02:30:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03521","created_at":"2026-07-05T02:30:18Z"},{"alias_kind":"pith_short_12","alias_value":"NU6JYNQO4BTR","created_at":"2026-07-05T02:30:18Z"},{"alias_kind":"pith_short_16","alias_value":"NU6JYNQO4BTR5MPC","created_at":"2026-07-05T02:30:18Z"},{"alias_kind":"pith_short_8","alias_value":"NU6JYNQO","created_at":"2026-07-05T02:30:18Z"}],"graph_snapshots":[{"event_id":"sha256:d5f20bda4db9ec83136c6930b27d2557482233b626815a7f4f9ef996346981c2","target":"graph","created_at":"2026-07-05T02:30:18Z","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/2104.03521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a multi-scale speech style modeling method for end-to-end expressive speech synthesis. The proposed method employs a multi-scale reference encoder to extract both the global-scale utterance-level and the local-scale quasi-phoneme-level style features of the target speech, which are then fed into the speech synthesis model as an extension to the input phoneme sequence. During training time, the multi-scale style model could be jointly trained with the speech synthesis model in an end-to-end fashion. By applying the proposed method to style transfer task, experimental resul","authors_text":"Changhe Song, Helen Meng, Jia Jia, Jingbei Li, Xiang Li, Zhiyong Wu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-08T05:50:09Z","title":"Towards Multi-Scale Style Control for Expressive Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03521","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":"sha256:5518439731bc835e5feaa96dd660625678bfae1319abe38b8e887b148281c6c1","target":"record","created_at":"2026-07-05T02:30:18Z","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":"c8119028b74b43fe46b5c68033984842baf4360eb1960a4645e0e09ab00aecf2","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-08T05:50:09Z","title_canon_sha256":"a0a7f0420bac60855f784a601bdd92e5f986348917294c89d309a1033f7e1400"},"schema_version":"1.0","source":{"id":"2104.03521","kind":"arxiv","version":1}},"canonical_sha256":"6d3c9c360ee0671eb1e2009576da01a568126a926a7fd363d166a36bc29d1861","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d3c9c360ee0671eb1e2009576da01a568126a926a7fd363d166a36bc29d1861","first_computed_at":"2026-07-05T02:30:18.379574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:18.379574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"756cmFrb7JB36NzADhjAx6gLjpudeJwdxTCKJCG+ej/d1WDLGEbrD6W7erFQKEMzOlBd7jNO9r6xY4wmhYlFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:18.380048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.03521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5518439731bc835e5feaa96dd660625678bfae1319abe38b8e887b148281c6c1","sha256:d5f20bda4db9ec83136c6930b27d2557482233b626815a7f4f9ef996346981c2"],"state_sha256":"8e2ccebef08acf5fedd1bb91e61d242dbec77c432c38181c7aa67f3808b5d152"}