{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IVYUG446HVDI3J4WRSL2MPJZA3","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":"24ed2cef74dcdcdb50e76b0c5a4da4954c2981615c600a63fe61970cfa19bea0","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-01-03T02:03:36Z","title_canon_sha256":"b63cc8b8cbc2d1e20e7344d85ade3df7dc423a1ccd667bc5a29c85aea6f1cce1"},"schema_version":"1.0","source":{"id":"2401.01498","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01498","created_at":"2026-07-05T09:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01498v1","created_at":"2026-07-05T09:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01498","created_at":"2026-07-05T09:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"IVYUG446HVDI","created_at":"2026-07-05T09:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"IVYUG446HVDI3J4W","created_at":"2026-07-05T09:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"IVYUG446","created_at":"2026-07-05T09:25:38Z"}],"graph_snapshots":[{"event_id":"sha256:ab5450b44c82985b1abc3f866d2d7e8ba58b0eb36331df34068a05c128d9e43b","target":"graph","created_at":"2026-07-05T09:25:38Z","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/2401.01498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from thes","authors_text":"Byoung Jin Choi, Joun Yeop Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Semin Kim","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-01-03T02:03:36Z","title":"Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01498","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:bb3716f5e612145cbea85538ae47b7669295bc9e8e44c786a335041572c43ce8","target":"record","created_at":"2026-07-05T09:25:38Z","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":"24ed2cef74dcdcdb50e76b0c5a4da4954c2981615c600a63fe61970cfa19bea0","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-01-03T02:03:36Z","title_canon_sha256":"b63cc8b8cbc2d1e20e7344d85ade3df7dc423a1ccd667bc5a29c85aea6f1cce1"},"schema_version":"1.0","source":{"id":"2401.01498","kind":"arxiv","version":1}},"canonical_sha256":"457143739e3d468da7968c97a63d3906d00557c43663f7acf88d71db6a900799","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"457143739e3d468da7968c97a63d3906d00557c43663f7acf88d71db6a900799","first_computed_at":"2026-07-05T09:25:38.224028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:38.224028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v86emoi+fLOygntHMgyZ6ksyOscZszg3p8uTDybq8Tf9DH/mIZ9SbjR80usfNjpLvKPB0rybldQDCjttavVvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:38.224493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01498","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb3716f5e612145cbea85538ae47b7669295bc9e8e44c786a335041572c43ce8","sha256:ab5450b44c82985b1abc3f866d2d7e8ba58b0eb36331df34068a05c128d9e43b"],"state_sha256":"e79ee04cffc24675d41cc33accade7d9101da1e09ee40325005ee2a3ea1d0524"}