{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GDP5MECT6EGHII4F2M65SYCOFM","short_pith_number":"pith:GDP5MECT","canonical_record":{"source":{"id":"2406.19135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T12:39:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94f521abeaecdca1e098568c4b42e3b7b24f5769e181f9601dbda44bae5e07bd","abstract_canon_sha256":"a1ca772e88caeac09d550f28a9477247ddf06b2308f3f5152e8524f5147763f7"},"schema_version":"1.0"},"canonical_sha256":"30dfd61053f10c742385d33dd9604e2b0c2cf1ca1ee58a29a68a82f9c33d3dbb","source":{"kind":"arxiv","id":"2406.19135","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GDP5MECT6EGHII4F2M65SYCOFM","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T12:39:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94f521abeaecdca1e098568c4b42e3b7b24f5769e181f9601dbda44bae5e07bd","abstract_canon_sha256":"a1ca772e88caeac09d550f28a9477247ddf06b2308f3f5152e8524f5147763f7"},"schema_version":"1.0"},"canonical_sha256":"30dfd61053f10c742385d33dd9604e2b0c2cf1ca1ee58a29a68a82f9c33d3dbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:30.683640Z","signature_b64":"ZU9ukSBfmxGChCRAw8kW8c5wonDE5hGv5+BGtu84JIHwF9LSFrYbWc+uedLyyl8N0h7kONi24DorKxmfv6YNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30dfd61053f10c742385d33dd9604e2b0c2cf1ca1ee58a29a68a82f9c33d3dbb","last_reissued_at":"2026-07-05T08:37:30.683142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:30.683142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19135","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHOOaeBaBzqC3RspXFkkkd58hWE4KsX6DY0yvhr4dwS5YCJtdsgfAhRdMy0XTpGcNFv9jxb2NN+lLVJJpLVoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:48:00.338805Z"},"content_sha256":"713766291be91ca0e1f065222110696146d90ef51717fb513e48fcfd69149091","schema_version":"1.0","event_id":"sha256:713766291be91ca0e1f065222110696146d90ef51717fb513e48fcfd69149091"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GDP5MECT6EGHII4F2M65SYCOFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Hyun Joon Park, Jin Sob Kim, Sung Won Han, Wooseok Shin","submitted_at":"2024-06-27T12:39:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19135","kind":"arxiv","version":1},"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/2406.19135/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSOY+2UdzB3XGfDUrgCR7c2Rfd/wrMi0X6Zf+zD9KD0IZ3rhpWPzyY2ozsNw1lD2VYj+jm4cRQgBzh3cqIGGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:48:00.339466Z"},"content_sha256":"2df37c587bcb61aeea49d06df1f750d2c14b465efd803a0fb755e165cc60305c","schema_version":"1.0","event_id":"sha256:2df37c587bcb61aeea49d06df1f750d2c14b465efd803a0fb755e165cc60305c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDP5MECT6EGHII4F2M65SYCOFM/bundle.json","state_url":"https://pith.science/pith/GDP5MECT6EGHII4F2M65SYCOFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDP5MECT6EGHII4F2M65SYCOFM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T23:48:00Z","links":{"resolver":"https://pith.science/pith/GDP5MECT6EGHII4F2M65SYCOFM","bundle":"https://pith.science/pith/GDP5MECT6EGHII4F2M65SYCOFM/bundle.json","state":"https://pith.science/pith/GDP5MECT6EGHII4F2M65SYCOFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDP5MECT6EGHII4F2M65SYCOFM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I++YpuJ5pdP1s0jT2dSqfknJIG6f5Y5EHiS3whx1pXkZbAsZY7ddhZhi9hxy84irM55hiKWqYRAiyc49FQ13CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:48:00.343411Z","bundle_sha256":"650efa6a6bc3dee9657cf321f39f1370238bb4a2f36982aa7c898033d1241cc0"}}