{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EXWYHLFDDLG75CK22SOQVJQEIH","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":"e27f9607501d0e10c999cefc7810c0ca5e21720a928e8e217469b8739ea7a08c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T08:05:11Z","title_canon_sha256":"e17f6eac26bc7e6515bff41e9e230cdf703890a4c8386b8cffecadbd74785140"},"schema_version":"1.0","source":{"id":"2106.15144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15144","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15144v1","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15144","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"pith_short_12","alias_value":"EXWYHLFDDLG7","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"pith_short_16","alias_value":"EXWYHLFDDLG75CK2","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"pith_short_8","alias_value":"EXWYHLFD","created_at":"2026-07-05T02:53:05Z"}],"graph_snapshots":[{"event_id":"sha256:70dfedc4e23f3a41405a50538d98ffec3d54004842e5cbe2f7a4c76a84a1b422","target":"graph","created_at":"2026-07-05T02:53:05Z","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/2106.15144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose methods for improving the modeling performance of a Transformer-based non-autoregressive text-to-speech (TNA-TTS) model. Although the text encoder and audio decoder handle different types and lengths of data (i.e., text and audio), the TNA-TTS models are not designed considering these variations. Therefore, to improve the modeling performance of the TNA-TTS model we propose a hierarchical Transformer structure-based text encoder and audio decoder that are designed to accommodate the characteristics of each module. For the text encoder, we constrain each self-attention","authors_text":"Hoon-Young Cho, Jae-Sung Bae, Tae-Jun Bak, Young-Sun Joo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T08:05:11Z","title":"Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15144","kind":"arxiv","version":1},"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":"sha256:32b840dbecef333f352b081c5a3e11988fd31dbe86591ce62ab1b3f8540c51f6","target":"record","created_at":"2026-07-05T02:53:05Z","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":"e27f9607501d0e10c999cefc7810c0ca5e21720a928e8e217469b8739ea7a08c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T08:05:11Z","title_canon_sha256":"e17f6eac26bc7e6515bff41e9e230cdf703890a4c8386b8cffecadbd74785140"},"schema_version":"1.0","source":{"id":"2106.15144","kind":"arxiv","version":1}},"canonical_sha256":"25ed83aca31acdfe895ad49d0aa60441cb1be21b54c08d9c0b4f7b6b4f76589a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25ed83aca31acdfe895ad49d0aa60441cb1be21b54c08d9c0b4f7b6b4f76589a","first_computed_at":"2026-07-05T02:53:05.783357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:53:05.783357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5TCGNonjOLkSr1AQJhbs0lAr8Mx6rD4ASeO1b152JnEsmc9OjwiOFIwSy4O4QCmXLAwBPUDf2VVf1+l52rz4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:53:05.783764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.15144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32b840dbecef333f352b081c5a3e11988fd31dbe86591ce62ab1b3f8540c51f6","sha256:70dfedc4e23f3a41405a50538d98ffec3d54004842e5cbe2f7a4c76a84a1b422"],"state_sha256":"f0a9ae1e4fadbe7bb4136a9aa521ac9f1bd07323922c4e8ffe20e7927a71619d"}