{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GDP5MECT6EGHII4F2M65SYCOFM","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":"a1ca772e88caeac09d550f28a9477247ddf06b2308f3f5152e8524f5147763f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T12:39:55Z","title_canon_sha256":"94f521abeaecdca1e098568c4b42e3b7b24f5769e181f9601dbda44bae5e07bd"},"schema_version":"1.0","source":{"id":"2406.19135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19135","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19135v1","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19135","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_12","alias_value":"GDP5MECT6EGH","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_16","alias_value":"GDP5MECT6EGHII4F","created_at":"2026-07-05T08:37:30Z"},{"alias_kind":"pith_short_8","alias_value":"GDP5MECT","created_at":"2026-07-05T08:37:30Z"}],"graph_snapshots":[{"event_id":"sha256:2df37c587bcb61aeea49d06df1f750d2c14b465efd803a0fb755e165cc60305c","target":"graph","created_at":"2026-07-05T08:37:30Z","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/2406.19135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive Text-to-Speech (TTS) using reference speech has been studied extensively to synthesize natural speech, but there are limitations to obtaining well-represented styles and improving model generalization ability. In this study, we present Diffusion-based EXpressive TTS (DEX-TTS), an acoustic model designed for reference-based speech synthesis with enhanced style representations. Based on a general diffusion TTS framework, DEX-TTS includes encoders and adapters to handle styles extracted from reference speech. Key innovations contain the differentiation of styles into time-invariant and","authors_text":"Hyun Joon Park, Jin Sob Kim, Sung Won Han, Wooseok Shin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T12:39:55Z","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19135","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":"sha256:713766291be91ca0e1f065222110696146d90ef51717fb513e48fcfd69149091","target":"record","created_at":"2026-07-05T08:37:30Z","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":"a1ca772e88caeac09d550f28a9477247ddf06b2308f3f5152e8524f5147763f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T12:39:55Z","title_canon_sha256":"94f521abeaecdca1e098568c4b42e3b7b24f5769e181f9601dbda44bae5e07bd"},"schema_version":"1.0","source":{"id":"2406.19135","kind":"arxiv","version":1}},"canonical_sha256":"30dfd61053f10c742385d33dd9604e2b0c2cf1ca1ee58a29a68a82f9c33d3dbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30dfd61053f10c742385d33dd9604e2b0c2cf1ca1ee58a29a68a82f9c33d3dbb","first_computed_at":"2026-07-05T08:37:30.683142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:30.683142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZU9ukSBfmxGChCRAw8kW8c5wonDE5hGv5+BGtu84JIHwF9LSFrYbWc+uedLyyl8N0h7kONi24DorKxmfv6YNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:30.683640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:713766291be91ca0e1f065222110696146d90ef51717fb513e48fcfd69149091","sha256:2df37c587bcb61aeea49d06df1f750d2c14b465efd803a0fb755e165cc60305c"],"state_sha256":"8a0b606bad1c31887b1280ebb643abeed97be5589da13ae20fad2b9d6c90486b"}