{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HDY7ZZOWRKO2DCSEKL5BA5UE4Q","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":"0b71458a97c8419dd6345500f0cd1a5eb319189819bc967accd5cfe17817eeec","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-08-23T23:45:48Z","title_canon_sha256":"e67b1b4d379603ba35a3107bf7dd4b103cb21339be628d464d39a313430a22bb"},"schema_version":"1.0","source":{"id":"2108.10447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.10447","created_at":"2026-07-05T03:08:09Z"},{"alias_kind":"arxiv_version","alias_value":"2108.10447v1","created_at":"2026-07-05T03:08:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10447","created_at":"2026-07-05T03:08:09Z"},{"alias_kind":"pith_short_12","alias_value":"HDY7ZZOWRKO2","created_at":"2026-07-05T03:08:09Z"},{"alias_kind":"pith_short_16","alias_value":"HDY7ZZOWRKO2DCSE","created_at":"2026-07-05T03:08:09Z"},{"alias_kind":"pith_short_8","alias_value":"HDY7ZZOW","created_at":"2026-07-05T03:08:09Z"}],"graph_snapshots":[{"event_id":"sha256:848454863eb7226610d55dccdd95ba0aa552eed08db57b3f8dfdafac0a48f821","target":"graph","created_at":"2026-07-05T03:08:09Z","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/2108.10447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line. However, these alignments tend to be brittle and often fail to generalize to long utterances and out-of-domain text, leading to missing or repeating words. Most non-autoregressive endto-end TTS models rely on durations extracted from external sources. In this paper we leverage the alignment mechanism proposed in RAD-TTS as a generic alignment learning framework, easily applicable to a variety of neural TTS model","authors_text":"Adrian {\\L}ancucki, Bryan Catanzaro, Kevin J. Shih, Rafael Valle, Rohan Badlani, Wei Ping","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-08-23T23:45:48Z","title":"One TTS Alignment To Rule Them All"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10447","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":"sha256:76438b1d43c6ec14c2f5547be02877ab0c879863ed3e452d81590743d55715fd","target":"record","created_at":"2026-07-05T03:08:09Z","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":"0b71458a97c8419dd6345500f0cd1a5eb319189819bc967accd5cfe17817eeec","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-08-23T23:45:48Z","title_canon_sha256":"e67b1b4d379603ba35a3107bf7dd4b103cb21339be628d464d39a313430a22bb"},"schema_version":"1.0","source":{"id":"2108.10447","kind":"arxiv","version":1}},"canonical_sha256":"38f1fce5d68a9da18a4452fa107684e43396af8257f825c12ff3a27b33ce9db5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38f1fce5d68a9da18a4452fa107684e43396af8257f825c12ff3a27b33ce9db5","first_computed_at":"2026-07-05T03:08:09.740000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:08:09.740000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dsxougYTRfPrv8YArjbm+UX5WWHeTXyNUEYhQYK/b8ZyE+UJwADUAVRlzvgemt2792qiQsqDRBZKwg15moMiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:08:09.740352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.10447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76438b1d43c6ec14c2f5547be02877ab0c879863ed3e452d81590743d55715fd","sha256:848454863eb7226610d55dccdd95ba0aa552eed08db57b3f8dfdafac0a48f821"],"state_sha256":"3f714bb402a09c24ccef3149cbae21af47efcad6348673aac12fa42751520806"}