{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UCXLIP5FX2G7FQ5TSUVFJLBD7A","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":"ce9f3329937a0197d4d4559ad5c8424128405e06201cfdf3f7675712cf52497c","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-12T10:26:57Z","title_canon_sha256":"c8cff1d37c7d1b10c9df79e16943994f1e48192dac8379688909ce5f775b6f3f"},"schema_version":"1.0","source":{"id":"2102.06431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.06431","created_at":"2026-07-05T02:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2102.06431v1","created_at":"2026-07-05T02:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06431","created_at":"2026-07-05T02:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"UCXLIP5FX2G7","created_at":"2026-07-05T02:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"UCXLIP5FX2G7FQ5T","created_at":"2026-07-05T02:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"UCXLIP5F","created_at":"2026-07-05T02:14:48Z"}],"graph_snapshots":[{"event_id":"sha256:5f384c027c5875cefce9af1e6e5f5fb1de7fb5d66810c1b93dc754a9c2717398","target":"graph","created_at":"2026-07-05T02:14:48Z","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/2102.06431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech (TTS) model using a very deep Variational Autoencoder (VDVAE) with Residual Attention mechanism, which refines the textual-to-acoustic alignment layer-wisely. Hierarchical latent variables with different temporal resolutions from the VDVAE are used as queries for residual attention module. By leveraging the coarse global alignment from previous attention layer as an extra input, the following attention layer can produce a refined version of alignment. This amortizes the burden of learning the textual-to-acoustic alignme","authors_text":"Chao Weng, Dan Su, Guangzhi Li, Na Hu, Peng Liu, Songxiang Liu, Yuewen Cao","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-12T10:26:57Z","title":"VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06431","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":"sha256:4bee4be67b9b8f07b4b481378b7239160f0b94131cdc1ecaba606d1ba925e7e9","target":"record","created_at":"2026-07-05T02:14:48Z","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":"ce9f3329937a0197d4d4559ad5c8424128405e06201cfdf3f7675712cf52497c","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-12T10:26:57Z","title_canon_sha256":"c8cff1d37c7d1b10c9df79e16943994f1e48192dac8379688909ce5f775b6f3f"},"schema_version":"1.0","source":{"id":"2102.06431","kind":"arxiv","version":1}},"canonical_sha256":"a0aeb43fa5be8df2c3b3952a54ac23f835682abf4aa7586793043598dcdabf98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0aeb43fa5be8df2c3b3952a54ac23f835682abf4aa7586793043598dcdabf98","first_computed_at":"2026-07-05T02:14:48.029355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:48.029355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7okEM1DI03FaTquQEzLKtVmEQnKDxcu8Kt2+xwRnrxE3Jl/Oy+KaUyJvwyD6mIR/NFQeBYazrkYRkPJkNmtkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:48.029870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.06431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bee4be67b9b8f07b4b481378b7239160f0b94131cdc1ecaba606d1ba925e7e9","sha256:5f384c027c5875cefce9af1e6e5f5fb1de7fb5d66810c1b93dc754a9c2717398"],"state_sha256":"a7b72cd3b653ce219c0242cabb6689433f19faef8dcb2f6d65e5566352876ad1"}