{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GCNFDSLR4JPHSP5GKY6UUMY2WU","short_pith_number":"pith:GCNFDSLR","canonical_record":{"source":{"id":"1906.00672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T09:52:19Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"283d80367f1d2417e22dbc9853628a5a053b51c040137599faf68cb295296f62","abstract_canon_sha256":"e3d821e677725dff9cd4f0b299c95a86af4ea537dd0df4fca173ce24d30e6077"},"schema_version":"1.0"},"canonical_sha256":"309a51c971e25e793fa6563d4a331ab53ee4cabda68b07e4b187c726c5494fe0","source":{"kind":"arxiv","id":"1906.00672","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GCNFDSLR4JPHSP5GKY6UUMY2WU","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-03T09:52:19Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"283d80367f1d2417e22dbc9853628a5a053b51c040137599faf68cb295296f62","abstract_canon_sha256":"e3d821e677725dff9cd4f0b299c95a86af4ea537dd0df4fca173ce24d30e6077"},"schema_version":"1.0"},"canonical_sha256":"309a51c971e25e793fa6563d4a331ab53ee4cabda68b07e4b187c726c5494fe0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:43.948595Z","signature_b64":"UUe0AhbQvNJdwZ49dznLsAwVmgJBFEJwDM9XApZl2aNFs81R3FL1lVf22tT+tqViJiDHxjGtiNt3+f/eQ6SoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"309a51c971e25e793fa6563d4a331ab53ee4cabda68b07e4b187c726c5494fe0","last_reissued_at":"2026-07-04T23:51:43.948124Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:43.948124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00672","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:51:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f1y/ajneU4X8bIAZfTk0DQOrlcGAWsKncCM3EUwJcp5/mSwCiHZqYnGyfs/1PQqXoXt7jVsxOZ5Dbkgeiv7pAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:14:01.844682Z"},"content_sha256":"d23c21354963947c8aa0b16c54d170c6dae08891424ccb3bb474a08845dd1575","schema_version":"1.0","event_id":"sha256:d23c21354963947c8aa0b16c54d170c6dae08891424ccb3bb474a08845dd1575"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GCNFDSLR4JPHSP5GKY6UUMY2WU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lei He, Mutian He, Yan Deng","submitted_at":"2019-06-03T09:52:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00672","kind":"arxiv","version":3},"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/1906.00672/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":"2026-07-04T23:51:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2TQWKV87+Yo1uNL+sYuC1RM2wAOZZRWimutUCLoggqku2cl8mVk/JAb13ROfCgcX1mOicU6434Rz39wirAqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:14:01.845211Z"},"content_sha256":"ffc466ce5f43289fde9d0149f7dd1adbdd38e570584ebd2aead1e6a6a965e9e7","schema_version":"1.0","event_id":"sha256:ffc466ce5f43289fde9d0149f7dd1adbdd38e570584ebd2aead1e6a6a965e9e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/bundle.json","state_url":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/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":"2026-08-10T18:14:01Z","links":{"resolver":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU","bundle":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/bundle.json","state":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XjNJXNk2iPdL3AuXROn5o0kH/mzFIAyFwXJ2xmhwwrGMrDfadWBeWtQ+2O6VMT+E3wt63ZCo8dvriRZkuEGaCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:14:01.850503Z","bundle_sha256":"3e7fc6baa7b3d9cb7a472d4c77c371b6d0e0db9fd273ea62b305c913721515b9"}}