{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5EZYZK4J633DAKXL7U76XT4BYL","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":"1c5ba761a5fc87c8a60bbfce35aa419e0f2d69704c8c2cc0f7a1d0ea0d474003","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-17T07:34:04Z","title_canon_sha256":"62d5cabf7020e24556acb468381735810fb9a7ab744c2882167206e2837e8b14"},"schema_version":"1.0","source":{"id":"2410.13288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13288","created_at":"2026-07-05T09:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13288v1","created_at":"2026-07-05T09:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13288","created_at":"2026-07-05T09:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"5EZYZK4J633D","created_at":"2026-07-05T09:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"5EZYZK4J633DAKXL","created_at":"2026-07-05T09:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"5EZYZK4J","created_at":"2026-07-05T09:21:58Z"}],"graph_snapshots":[{"event_id":"sha256:ff41b5afe395706e6d1db86d78daadf809a321d635b5cfda975a3c53596b64bb","target":"graph","created_at":"2026-07-05T09:21:58Z","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/2410.13288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes an improved version of DurIAN-E (DurIAN-E 2), which is also a duration informed attention neural network for expressive and high-fidelity text-to-speech (TTS) synthesis. Similar with the DurIAN-E model, multiple stacked SwishRNN-based Transformer blocks are utilized as linguistic encoders and Style-Adaptive Instance Normalization (SAIN) layers are also exploited into frame-level encoders to improve the modeling ability of expressiveness in the proposed the DurIAN-E 2. Meanwhile, motivated by other TTS models using generative models such as VITS, the proposed DurIAN-E 2 util","authors_text":"Chao Weng, Dan Su, Guangzhi Lei, Qiushi Zhu, Yu Gu","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-17T07:34:04Z","title":"DurIAN-E 2: Duration Informed Attention Network with Adaptive Variational Autoencoder and Adversarial Learning for Expressive Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13288","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:eda7827b140397bcb201880abaf9e307acc76791879254a680cb01b075c7fca2","target":"record","created_at":"2026-07-05T09:21:58Z","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":"1c5ba761a5fc87c8a60bbfce35aa419e0f2d69704c8c2cc0f7a1d0ea0d474003","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-17T07:34:04Z","title_canon_sha256":"62d5cabf7020e24556acb468381735810fb9a7ab744c2882167206e2837e8b14"},"schema_version":"1.0","source":{"id":"2410.13288","kind":"arxiv","version":1}},"canonical_sha256":"e9338cab89f6f6302aebfd3febcf81c2d3acfd49a1e9dd44d6244b17b3133434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9338cab89f6f6302aebfd3febcf81c2d3acfd49a1e9dd44d6244b17b3133434","first_computed_at":"2026-07-05T09:21:58.095933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:58.095933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QbU1iiqyCaisAJcg394HuqG914kWcZg18xGwWj1FfxNiUpL4d0lKIuSzGUxnPrNGh8XZcAW2fIhQ7Cx0jiKEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:58.096407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eda7827b140397bcb201880abaf9e307acc76791879254a680cb01b075c7fca2","sha256:ff41b5afe395706e6d1db86d78daadf809a321d635b5cfda975a3c53596b64bb"],"state_sha256":"3ef32e4df321c3667090d825d2e35cf04fd5a9310fa2b104d17d393703741a44"}