{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DBVEKV3D2YYPSCUY44U5573QGR","short_pith_number":"pith:DBVEKV3D","schema_version":"1.0","canonical_sha256":"186a455763d630f90a98e729deff703476893bfce0aa2a95d8c9f95ed880919e","source":{"kind":"arxiv","id":"1810.11960","version":2},"attestation_state":"computed","paper":{"title":"Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Junichi Yamagishi, Shinji Takaki, Xin Wang, Yusuke Yasuda","submitted_at":"2018-10-29T05:25:21Z","abstract_excerpt":"End-to-end speech synthesis is a promising approach that directly converts raw text to speech. Although it was shown that Tacotron2 outperforms classical pipeline systems with regards to naturalness in English, its applicability to other languages is still unknown. Japanese could be one of the most difficult languages for which to achieve end-to-end speech synthesis, largely due to its character diversity and pitch accents. Therefore, state-of-the-art systems are still based on a traditional pipeline framework that requires a separate text analyzer and duration model. Towards end-to-end Japane"},"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":"1810.11960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2018-10-29T05:25:21Z","cross_cats_sorted":["cs.CL","cs.SD","stat.ML"],"title_canon_sha256":"23dc5784bc552779f4f96e451289bde21ab6d10e421a5f0d500931c448c75720","abstract_canon_sha256":"232989842c6e412bf30cf696d51a256b9faf841c734da56765b15b9691aef5a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:02.422635Z","signature_b64":"UXu2XZBJukTPMvJC4D/Gyj1lgvEgHDBKf675ZKq0wdTlaRFp1Dh/CFb30Gx6G+wlQH7qqBF8T+wJj1lRavbLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"186a455763d630f90a98e729deff703476893bfce0aa2a95d8c9f95ed880919e","last_reissued_at":"2026-05-17T23:54:02.422056Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:02.422056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Junichi Yamagishi, Shinji Takaki, Xin Wang, Yusuke Yasuda","submitted_at":"2018-10-29T05:25:21Z","abstract_excerpt":"End-to-end speech synthesis is a promising approach that directly converts raw text to speech. Although it was shown that Tacotron2 outperforms classical pipeline systems with regards to naturalness in English, its applicability to other languages is still unknown. Japanese could be one of the most difficult languages for which to achieve end-to-end speech synthesis, largely due to its character diversity and pitch accents. Therefore, state-of-the-art systems are still based on a traditional pipeline framework that requires a separate text analyzer and duration model. Towards end-to-end Japane"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11960","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":""},"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":"1810.11960","created_at":"2026-05-17T23:54:02.422160+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11960v2","created_at":"2026-05-17T23:54:02.422160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11960","created_at":"2026-05-17T23:54:02.422160+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBVEKV3D2YYP","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBVEKV3D2YYPSCUY","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBVEKV3D","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR","json":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR.json","graph_json":"https://pith.science/api/pith-number/DBVEKV3D2YYPSCUY44U5573QGR/graph.json","events_json":"https://pith.science/api/pith-number/DBVEKV3D2YYPSCUY44U5573QGR/events.json","paper":"https://pith.science/paper/DBVEKV3D"},"agent_actions":{"view_html":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR","download_json":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR.json","view_paper":"https://pith.science/paper/DBVEKV3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11960&json=true","fetch_graph":"https://pith.science/api/pith-number/DBVEKV3D2YYPSCUY44U5573QGR/graph.json","fetch_events":"https://pith.science/api/pith-number/DBVEKV3D2YYPSCUY44U5573QGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR/action/storage_attestation","attest_author":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR/action/author_attestation","sign_citation":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR/action/citation_signature","submit_replication":"https://pith.science/pith/DBVEKV3D2YYPSCUY44U5573QGR/action/replication_record"}},"created_at":"2026-05-17T23:54:02.422160+00:00","updated_at":"2026-05-17T23:54:02.422160+00:00"}