{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KHJTI6F7I3PDSEOXHYYS5DVSBI","short_pith_number":"pith:KHJTI6F7","canonical_record":{"source":{"id":"2309.12792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-22T11:06:04Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"90e465584d9184e4db154053f9235dbbb59dbf7850ec1271a009ea42ae9e58f4","abstract_canon_sha256":"37bef1b0a084f5af58da78270f73c0f2b0d8ad91682ec3dff1a21384e2007dc7"},"schema_version":"1.0"},"canonical_sha256":"51d33478bf46de3911d73e312e8eb20a28609402b2c1980d0589c4da77e2ca54","source":{"kind":"arxiv","id":"2309.12792","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12792","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12792v1","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12792","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"KHJTI6F7I3PD","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"KHJTI6F7I3PDSEOX","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"KHJTI6F7","created_at":"2026-07-05T06:53:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KHJTI6F7I3PDSEOXHYYS5DVSBI","target":"record","payload":{"canonical_record":{"source":{"id":"2309.12792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-22T11:06:04Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"90e465584d9184e4db154053f9235dbbb59dbf7850ec1271a009ea42ae9e58f4","abstract_canon_sha256":"37bef1b0a084f5af58da78270f73c0f2b0d8ad91682ec3dff1a21384e2007dc7"},"schema_version":"1.0"},"canonical_sha256":"51d33478bf46de3911d73e312e8eb20a28609402b2c1980d0589c4da77e2ca54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:17.881937Z","signature_b64":"Ut8RkbZp325JEUIK3ZmTi0uxHSGq+OWrnvb7Ql3Da9SYJCB4lMqXGsmrrbP6q3jot9I2dfBTRetkb9UEVsFZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51d33478bf46de3911d73e312e8eb20a28609402b2c1980d0589c4da77e2ca54","last_reissued_at":"2026-07-05T06:53:17.881528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:17.881528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.12792","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":"2026-07-05T06:53:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fyQ58FgQeRzte5iXy/c5psBw/TTcUnUiJkQU/ejiOsitIROYOx9ZsUhW7YaI1mDkS78xuDc/dvuUL6vTtmLkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:31:30.964512Z"},"content_sha256":"c90a2462f583da4f0ad0062cfb0edd52285e6f44c9f16a12c60d2ada63363ea2","schema_version":"1.0","event_id":"sha256:c90a2462f583da4f0ad0062cfb0edd52285e6f44c9f16a12c60d2ada63363ea2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KHJTI6F7I3PDSEOXHYYS5DVSBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DurIAN-E: Duration Informed Attention Network For Expressive Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chao Weng, Dan Su, Guangzhi Lei, Yianrao Bian, Yu Gu","submitted_at":"2023-09-22T11:06:04Z","abstract_excerpt":"This paper introduces an improved duration informed attention neural network (DurIAN-E) for expressive and high-fidelity text-to-speech (TTS) synthesis. Inherited from the original DurIAN model, an auto-regressive model structure in which the alignments between the input linguistic information and the output acoustic features are inferred from a duration model is adopted. Meanwhile the proposed DurIAN-E utilizes multiple stacked SwishRNN-based Transformer blocks as linguistic encoders. Style-Adaptive Instance Normalization (SAIN) layers are exploited into frame-level encoders to improve the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12792","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/2309.12792/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":"2026-07-05T06:53:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9rSRhuHginD8lnoyp7ZDaIiX8fRUh+j/4cOho38D+RxCt9m9NGRPczM+3blHTNB4Vrpkx5O/vHqROd+Bh2bDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:31:30.965278Z"},"content_sha256":"078c6b7f689b0b1222db11da1c88a4bd3dfb772eb820d5b8cdcc7106a7e730d7","schema_version":"1.0","event_id":"sha256:078c6b7f689b0b1222db11da1c88a4bd3dfb772eb820d5b8cdcc7106a7e730d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHJTI6F7I3PDSEOXHYYS5DVSBI/bundle.json","state_url":"https://pith.science/pith/KHJTI6F7I3PDSEOXHYYS5DVSBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHJTI6F7I3PDSEOXHYYS5DVSBI/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":"2026-08-18T20:31:30Z","links":{"resolver":"https://pith.science/pith/KHJTI6F7I3PDSEOXHYYS5DVSBI","bundle":"https://pith.science/pith/KHJTI6F7I3PDSEOXHYYS5DVSBI/bundle.json","state":"https://pith.science/pith/KHJTI6F7I3PDSEOXHYYS5DVSBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHJTI6F7I3PDSEOXHYYS5DVSBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KHJTI6F7I3PDSEOXHYYS5DVSBI","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":"37bef1b0a084f5af58da78270f73c0f2b0d8ad91682ec3dff1a21384e2007dc7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-22T11:06:04Z","title_canon_sha256":"90e465584d9184e4db154053f9235dbbb59dbf7850ec1271a009ea42ae9e58f4"},"schema_version":"1.0","source":{"id":"2309.12792","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12792","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12792v1","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12792","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"pith_short_12","alias_value":"KHJTI6F7I3PD","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"pith_short_16","alias_value":"KHJTI6F7I3PDSEOX","created_at":"2026-07-05T06:53:17Z"},{"alias_kind":"pith_short_8","alias_value":"KHJTI6F7","created_at":"2026-07-05T06:53:17Z"}],"graph_snapshots":[{"event_id":"sha256:078c6b7f689b0b1222db11da1c88a4bd3dfb772eb820d5b8cdcc7106a7e730d7","target":"graph","created_at":"2026-07-05T06:53:17Z","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/2309.12792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces an improved duration informed attention neural network (DurIAN-E) for expressive and high-fidelity text-to-speech (TTS) synthesis. Inherited from the original DurIAN model, an auto-regressive model structure in which the alignments between the input linguistic information and the output acoustic features are inferred from a duration model is adopted. Meanwhile the proposed DurIAN-E utilizes multiple stacked SwishRNN-based Transformer blocks as linguistic encoders. Style-Adaptive Instance Normalization (SAIN) layers are exploited into frame-level encoders to improve the mo","authors_text":"Chao Weng, Dan Su, Guangzhi Lei, Yianrao Bian, Yu Gu","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-22T11:06:04Z","title":"DurIAN-E: Duration Informed Attention Network For Expressive Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12792","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:c90a2462f583da4f0ad0062cfb0edd52285e6f44c9f16a12c60d2ada63363ea2","target":"record","created_at":"2026-07-05T06:53:17Z","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":"37bef1b0a084f5af58da78270f73c0f2b0d8ad91682ec3dff1a21384e2007dc7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-22T11:06:04Z","title_canon_sha256":"90e465584d9184e4db154053f9235dbbb59dbf7850ec1271a009ea42ae9e58f4"},"schema_version":"1.0","source":{"id":"2309.12792","kind":"arxiv","version":1}},"canonical_sha256":"51d33478bf46de3911d73e312e8eb20a28609402b2c1980d0589c4da77e2ca54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51d33478bf46de3911d73e312e8eb20a28609402b2c1980d0589c4da77e2ca54","first_computed_at":"2026-07-05T06:53:17.881528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:17.881528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ut8RkbZp325JEUIK3ZmTi0uxHSGq+OWrnvb7Ql3Da9SYJCB4lMqXGsmrrbP6q3jot9I2dfBTRetkb9UEVsFZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:17.881937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12792","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c90a2462f583da4f0ad0062cfb0edd52285e6f44c9f16a12c60d2ada63363ea2","sha256:078c6b7f689b0b1222db11da1c88a4bd3dfb772eb820d5b8cdcc7106a7e730d7"],"state_sha256":"ba8b6fafc08595f55bec6f1eae5e9f4ce6aefd960604d53ef5f4c864a4e691fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UnoVjnmprwOBHlR+MEHAbLRnt6nVBpaqj1t0VfQi8fSHXSLNekUYqZ7dA/hlZ8PBu4mCv8V938+rRIDe5Hf3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:31:30.971433Z","bundle_sha256":"689c9b4335d3cd7e44c65d4532759febfef54db29076a6c5d7c1c979fa7ddf78"}}