{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GCNFDSLR4JPHSP5GKY6UUMY2WU","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":"e3d821e677725dff9cd4f0b299c95a86af4ea537dd0df4fca173ce24d30e6077","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T09:52:19Z","title_canon_sha256":"283d80367f1d2417e22dbc9853628a5a053b51c040137599faf68cb295296f62"},"schema_version":"1.0","source":{"id":"1906.00672","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00672","created_at":"2026-07-04T23:51:43Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00672v3","created_at":"2026-07-04T23:51:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00672","created_at":"2026-07-04T23:51:43Z"},{"alias_kind":"pith_short_12","alias_value":"GCNFDSLR4JPH","created_at":"2026-07-04T23:51:43Z"},{"alias_kind":"pith_short_16","alias_value":"GCNFDSLR4JPHSP5G","created_at":"2026-07-04T23:51:43Z"},{"alias_kind":"pith_short_8","alias_value":"GCNFDSLR","created_at":"2026-07-04T23:51:43Z"}],"graph_snapshots":[{"event_id":"sha256:ffc466ce5f43289fde9d0149f7dd1adbdd38e570584ebd2aead1e6a6a965e9e7","target":"graph","created_at":"2026-07-04T23:51:43Z","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/1906.00672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural TTS has demonstrated strong capabilities to generate human-like speech with high quality and naturalness, while its generalization to out-of-domain texts is still a challenging task, with regard to the design of attention-based sequence-to-sequence acoustic modeling. Various errors occur in those inputs with unseen context, including attention collapse, skipping, repeating, etc., which limits the broader applications. In this paper, we propose a novel stepwise monotonic attention method in sequence-to-sequence acoustic modeling to improve the robustness on out-of-domain inputs. The meth","authors_text":"Lei He, Mutian He, Yan Deng","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T09:52:19Z","title":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00672","kind":"arxiv","version":3},"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:d23c21354963947c8aa0b16c54d170c6dae08891424ccb3bb474a08845dd1575","target":"record","created_at":"2026-07-04T23:51:43Z","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":"e3d821e677725dff9cd4f0b299c95a86af4ea537dd0df4fca173ce24d30e6077","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T09:52:19Z","title_canon_sha256":"283d80367f1d2417e22dbc9853628a5a053b51c040137599faf68cb295296f62"},"schema_version":"1.0","source":{"id":"1906.00672","kind":"arxiv","version":3}},"canonical_sha256":"309a51c971e25e793fa6563d4a331ab53ee4cabda68b07e4b187c726c5494fe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"309a51c971e25e793fa6563d4a331ab53ee4cabda68b07e4b187c726c5494fe0","first_computed_at":"2026-07-04T23:51:43.948124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:43.948124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UUe0AhbQvNJdwZ49dznLsAwVmgJBFEJwDM9XApZl2aNFs81R3FL1lVf22tT+tqViJiDHxjGtiNt3+f/eQ6SoAA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:43.948595Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00672","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d23c21354963947c8aa0b16c54d170c6dae08891424ccb3bb474a08845dd1575","sha256:ffc466ce5f43289fde9d0149f7dd1adbdd38e570584ebd2aead1e6a6a965e9e7"],"state_sha256":"ea81236a320df8a938b134934c82b8a4b25d12a3f9fbf5b93172f17b6ad3062d"}