{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EXWYHLFDDLG75CK22SOQVJQEIH","short_pith_number":"pith:EXWYHLFD","schema_version":"1.0","canonical_sha256":"25ed83aca31acdfe895ad49d0aa60441cb1be21b54c08d9c0b4f7b6b4f76589a","source":{"kind":"arxiv","id":"2106.15144","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hoon-Young Cho, Jae-Sung Bae, Tae-Jun Bak, Young-Sun Joo","submitted_at":"2021-06-29T08:05:11Z","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"},"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":"2106.15144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T08:05:11Z","cross_cats_sorted":[],"title_canon_sha256":"e17f6eac26bc7e6515bff41e9e230cdf703890a4c8386b8cffecadbd74785140","abstract_canon_sha256":"e27f9607501d0e10c999cefc7810c0ca5e21720a928e8e217469b8739ea7a08c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:05.783764Z","signature_b64":"5TCGNonjOLkSr1AQJhbs0lAr8Mx6rD4ASeO1b152JnEsmc9OjwiOFIwSy4O4QCmXLAwBPUDf2VVf1+l52rz4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ed83aca31acdfe895ad49d0aa60441cb1be21b54c08d9c0b4f7b6b4f76589a","last_reissued_at":"2026-07-05T02:53:05.783357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:05.783357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hoon-Young Cho, Jae-Sung Bae, Tae-Jun Bak, Young-Sun Joo","submitted_at":"2021-06-29T08:05:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15144","kind":"arxiv","version":1},"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/2106.15144/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":"2106.15144","created_at":"2026-07-05T02:53:05.783415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15144v1","created_at":"2026-07-05T02:53:05.783415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15144","created_at":"2026-07-05T02:53:05.783415+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXWYHLFDDLG7","created_at":"2026-07-05T02:53:05.783415+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXWYHLFDDLG75CK2","created_at":"2026-07-05T02:53:05.783415+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXWYHLFD","created_at":"2026-07-05T02:53:05.783415+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/EXWYHLFDDLG75CK22SOQVJQEIH","json":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH.json","graph_json":"https://pith.science/api/pith-number/EXWYHLFDDLG75CK22SOQVJQEIH/graph.json","events_json":"https://pith.science/api/pith-number/EXWYHLFDDLG75CK22SOQVJQEIH/events.json","paper":"https://pith.science/paper/EXWYHLFD"},"agent_actions":{"view_html":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH","download_json":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH.json","view_paper":"https://pith.science/paper/EXWYHLFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15144&json=true","fetch_graph":"https://pith.science/api/pith-number/EXWYHLFDDLG75CK22SOQVJQEIH/graph.json","fetch_events":"https://pith.science/api/pith-number/EXWYHLFDDLG75CK22SOQVJQEIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH/action/storage_attestation","attest_author":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH/action/author_attestation","sign_citation":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH/action/citation_signature","submit_replication":"https://pith.science/pith/EXWYHLFDDLG75CK22SOQVJQEIH/action/replication_record"}},"created_at":"2026-07-05T02:53:05.783415+00:00","updated_at":"2026-07-05T02:53:05.783415+00:00"}