{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NNWO3T2QS6Y3PMZ2PV4NWSYWU7","short_pith_number":"pith:NNWO3T2Q","canonical_record":{"source":{"id":"1909.01700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T11:35:48Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"b6ee55a4c54144fbca9ef2e023b9d151b2a39cc5280a9b1315e8db7d6f81f7a0","abstract_canon_sha256":"6810f42fce5c219ee5c3d1b51c2db3fbb16c5753125cbddd64402f2dbdb92df2"},"schema_version":"1.0"},"canonical_sha256":"6b6cedcf5097b1b7b33a7d78db4b16a7d7fdca0bcd9f1c870ce85f8aaf9fbf8d","source":{"kind":"arxiv","id":"1909.01700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01700","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01700v2","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01700","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"NNWO3T2QS6Y3","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"pith_short_16","alias_value":"NNWO3T2QS6Y3PMZ2","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"pith_short_8","alias_value":"NNWO3T2Q","created_at":"2026-07-05T00:02:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NNWO3T2QS6Y3PMZ2PV4NWSYWU7","target":"record","payload":{"canonical_record":{"source":{"id":"1909.01700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T11:35:48Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"b6ee55a4c54144fbca9ef2e023b9d151b2a39cc5280a9b1315e8db7d6f81f7a0","abstract_canon_sha256":"6810f42fce5c219ee5c3d1b51c2db3fbb16c5753125cbddd64402f2dbdb92df2"},"schema_version":"1.0"},"canonical_sha256":"6b6cedcf5097b1b7b33a7d78db4b16a7d7fdca0bcd9f1c870ce85f8aaf9fbf8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:40.370807Z","signature_b64":"SWJtPfsynSWD+sA9HAUH///tSd4m4LYpZoCSgCjsFWmyjkr88bT3c2y1ZlH7bJzbP77b5ZJiZAQUN8YCn434Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b6cedcf5097b1b7b33a7d78db4b16a7d7fdca0bcd9f1c870ce85f8aaf9fbf8d","last_reissued_at":"2026-07-05T00:02:40.370401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:40.370401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.01700","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rd0uYA4LjJFOuYfap7IzMdZqU/e2iId+GvM+ommGuNhf71++9kJEyFxOM+eVkhZ9sD08CpmorugVit4vUtcWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:42:51.378834Z"},"content_sha256":"db6b765cc4fb8418eef9688342bb5fa2299ffd1185a2702a677976c9fe93799a","schema_version":"1.0","event_id":"sha256:db6b765cc4fb8418eef9688342bb5fa2299ffd1185a2702a677976c9fe93799a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NNWO3T2QS6Y3PMZ2PV4NWSYWU7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DurIAN: Duration Informed Attention Network For Multimodal Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Weng, Chengzhu Yu, Dan Su, Deyi Tuo, Dong Yu, Guangzhi Lei, Heng Lu, Kun Xu, Meng Yu, Na Hu, Peng Liu, Shiyin Kang","submitted_at":"2019-09-04T11:35:48Z","abstract_excerpt":"In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously. The key component of this system is the Duration Informed Attention Network (DurIAN), an autoregressive model in which the alignments between the input text and the output acoustic features are inferred from a duration model. This is different from the end-to-end attention mechanism used, and accounts for various unavoidable artifacts, in existing end-to-end speech synthesis systems such as Tacotron. Furthermore, DurIAN can be used to generate hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01700","kind":"arxiv","version":2},"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/1909.01700/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":"2026-07-05T00:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iXZpcKOvTKNTbmf6gD5Mr96Q6v32mHIAATea4HzZItLhPKHyZzhr0xda8NDzmAaYlNgEAI5ie7RlU2wE/rTgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:42:51.379375Z"},"content_sha256":"c3be32b63c1147a93b8eb671e0633f3df8f0b8e1f83eb0d32eb096f2497eeb6e","schema_version":"1.0","event_id":"sha256:c3be32b63c1147a93b8eb671e0633f3df8f0b8e1f83eb0d32eb096f2497eeb6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNWO3T2QS6Y3PMZ2PV4NWSYWU7/bundle.json","state_url":"https://pith.science/pith/NNWO3T2QS6Y3PMZ2PV4NWSYWU7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNWO3T2QS6Y3PMZ2PV4NWSYWU7/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":"2026-08-03T14:42:51Z","links":{"resolver":"https://pith.science/pith/NNWO3T2QS6Y3PMZ2PV4NWSYWU7","bundle":"https://pith.science/pith/NNWO3T2QS6Y3PMZ2PV4NWSYWU7/bundle.json","state":"https://pith.science/pith/NNWO3T2QS6Y3PMZ2PV4NWSYWU7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNWO3T2QS6Y3PMZ2PV4NWSYWU7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NNWO3T2QS6Y3PMZ2PV4NWSYWU7","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":"6810f42fce5c219ee5c3d1b51c2db3fbb16c5753125cbddd64402f2dbdb92df2","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T11:35:48Z","title_canon_sha256":"b6ee55a4c54144fbca9ef2e023b9d151b2a39cc5280a9b1315e8db7d6f81f7a0"},"schema_version":"1.0","source":{"id":"1909.01700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01700","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01700v2","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01700","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"NNWO3T2QS6Y3","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"pith_short_16","alias_value":"NNWO3T2QS6Y3PMZ2","created_at":"2026-07-05T00:02:40Z"},{"alias_kind":"pith_short_8","alias_value":"NNWO3T2Q","created_at":"2026-07-05T00:02:40Z"}],"graph_snapshots":[{"event_id":"sha256:c3be32b63c1147a93b8eb671e0633f3df8f0b8e1f83eb0d32eb096f2497eeb6e","target":"graph","created_at":"2026-07-05T00:02:40Z","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/1909.01700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously. The key component of this system is the Duration Informed Attention Network (DurIAN), an autoregressive model in which the alignments between the input text and the output acoustic features are inferred from a duration model. This is different from the end-to-end attention mechanism used, and accounts for various unavoidable artifacts, in existing end-to-end speech synthesis systems such as Tacotron. Furthermore, DurIAN can be used to generate hig","authors_text":"Chao Weng, Chengzhu Yu, Dan Su, Deyi Tuo, Dong Yu, Guangzhi Lei, Heng Lu, Kun Xu, Meng Yu, Na Hu, Peng Liu, Shiyin Kang","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T11:35:48Z","title":"DurIAN: Duration Informed Attention Network For Multimodal Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01700","kind":"arxiv","version":2},"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:db6b765cc4fb8418eef9688342bb5fa2299ffd1185a2702a677976c9fe93799a","target":"record","created_at":"2026-07-05T00:02:40Z","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":"6810f42fce5c219ee5c3d1b51c2db3fbb16c5753125cbddd64402f2dbdb92df2","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T11:35:48Z","title_canon_sha256":"b6ee55a4c54144fbca9ef2e023b9d151b2a39cc5280a9b1315e8db7d6f81f7a0"},"schema_version":"1.0","source":{"id":"1909.01700","kind":"arxiv","version":2}},"canonical_sha256":"6b6cedcf5097b1b7b33a7d78db4b16a7d7fdca0bcd9f1c870ce85f8aaf9fbf8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b6cedcf5097b1b7b33a7d78db4b16a7d7fdca0bcd9f1c870ce85f8aaf9fbf8d","first_computed_at":"2026-07-05T00:02:40.370401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:40.370401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWJtPfsynSWD+sA9HAUH///tSd4m4LYpZoCSgCjsFWmyjkr88bT3c2y1ZlH7bJzbP77b5ZJiZAQUN8YCn434Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:40.370807Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db6b765cc4fb8418eef9688342bb5fa2299ffd1185a2702a677976c9fe93799a","sha256:c3be32b63c1147a93b8eb671e0633f3df8f0b8e1f83eb0d32eb096f2497eeb6e"],"state_sha256":"ac6aa839f5c63989a81c0aa8240c33b9fb131557da1d17440041c13578fee174"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+XpLKwSwOIAqpqTkn1mScYyDQN+K76GdT9uq9ud+iufYUj8NrSdKC4znAE4XKO9NSGciBq3/freaM8u1aBdmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T14:42:51.385558Z","bundle_sha256":"4309e622b3330154d7cbcb75ea7a771ccf5df256efd62f036c8a30dbacefe66c"}}