{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GCNFDSLR4JPHSP5GKY6UUMY2WU","short_pith_number":"pith:GCNFDSLR","schema_version":"1.0","canonical_sha256":"309a51c971e25e793fa6563d4a331ab53ee4cabda68b07e4b187c726c5494fe0","source":{"kind":"arxiv","id":"1906.00672","version":3},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.00672","created_at":"2026-07-04T23:51:43.948177+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00672v3","created_at":"2026-07-04T23:51:43.948177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00672","created_at":"2026-07-04T23:51:43.948177+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCNFDSLR4JPH","created_at":"2026-07-04T23:51:43.948177+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCNFDSLR4JPHSP5G","created_at":"2026-07-04T23:51:43.948177+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCNFDSLR","created_at":"2026-07-04T23:51:43.948177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01084","citing_title":"Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU","json":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU.json","graph_json":"https://pith.science/api/pith-number/GCNFDSLR4JPHSP5GKY6UUMY2WU/graph.json","events_json":"https://pith.science/api/pith-number/GCNFDSLR4JPHSP5GKY6UUMY2WU/events.json","paper":"https://pith.science/paper/GCNFDSLR"},"agent_actions":{"view_html":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU","download_json":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU.json","view_paper":"https://pith.science/paper/GCNFDSLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00672&json=true","fetch_graph":"https://pith.science/api/pith-number/GCNFDSLR4JPHSP5GKY6UUMY2WU/graph.json","fetch_events":"https://pith.science/api/pith-number/GCNFDSLR4JPHSP5GKY6UUMY2WU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/action/storage_attestation","attest_author":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/action/author_attestation","sign_citation":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/action/citation_signature","submit_replication":"https://pith.science/pith/GCNFDSLR4JPHSP5GKY6UUMY2WU/action/replication_record"}},"created_at":"2026-07-04T23:51:43.948177+00:00","updated_at":"2026-07-04T23:51:43.948177+00:00"}