{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TNPK7Y7GNSSHQCOYAGC2Y5M7CZ","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":"5ea8c3a1b29e9440750b4322cb332e80dcd01d04adf55484edf16d435b0c8f8e","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-07-07T15:32:36Z","title_canon_sha256":"46b642be43939e379b8bffb0b89f96dd6f3d887bd9f25e4039de36d347edd390"},"schema_version":"1.0","source":{"id":"2107.03298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.03298","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.03298v1","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03298","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"pith_short_12","alias_value":"TNPK7Y7GNSSH","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"pith_short_16","alias_value":"TNPK7Y7GNSSHQCOY","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"pith_short_8","alias_value":"TNPK7Y7G","created_at":"2026-07-05T02:56:02Z"}],"graph_snapshots":[{"event_id":"sha256:833d305d3719a743d4a55c34e00b4744bd306a7344f9985a91fe0b26773cd310","target":"graph","created_at":"2026-07-05T02:56:02Z","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/2107.03298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes a variational auto-encoder based non-autoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequence-to-sequence architecture can generate high-quality speech, but their sequential decoding process can be time-consuming. Recently, non-autoregressive TTS (NAR-TTS) models have been shown to be more efficient with the parallel decoding process. However, these NAR-TTS models rely on phoneme-level durations to generate a hard alignment between the text and the spectrogram. Obtaining duration labels, either through forced alignment ","authors_text":"Helen Meng, Hui Lu, Shiyin Kang, Xixin Wu, Xu Li, Xunying Liu, Zhiyong Wu","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-07-07T15:32:36Z","title":"VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03298","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:da35dc91d6f8749a4ebb5d2c4422be5538f0e84f654d1227f4802861dddb1db8","target":"record","created_at":"2026-07-05T02:56:02Z","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":"5ea8c3a1b29e9440750b4322cb332e80dcd01d04adf55484edf16d435b0c8f8e","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-07-07T15:32:36Z","title_canon_sha256":"46b642be43939e379b8bffb0b89f96dd6f3d887bd9f25e4039de36d347edd390"},"schema_version":"1.0","source":{"id":"2107.03298","kind":"arxiv","version":1}},"canonical_sha256":"9b5eafe3e66ca47809d80185ac759f16731012104282da85a9075dbd50c2803d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b5eafe3e66ca47809d80185ac759f16731012104282da85a9075dbd50c2803d","first_computed_at":"2026-07-05T02:56:02.527895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:02.527895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PmSIlaaiVNaEPBHrLDpyBC0X1jeqewiipgFzpr5BASknEfDGi2I5z4qpnG4DaC5trbA+GejijXT50sJA97SoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:02.528233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.03298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da35dc91d6f8749a4ebb5d2c4422be5538f0e84f654d1227f4802861dddb1db8","sha256:833d305d3719a743d4a55c34e00b4744bd306a7344f9985a91fe0b26773cd310"],"state_sha256":"a3a81cd6018cfca0ad43ee9fdcd479c18bcc85f6d7133f0a02474b5d359eb750"}