{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FN7O74TUI4KPAKC24PLKZQP6VY","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":"84f4b39fee304fd3b83883838f623ac1de755f3380bdabf76a4521e0f1fa67b1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-06T06:13:39Z","title_canon_sha256":"8d6c20cdb01745a9e24c7bffd136af3186429b11791502319ca8cfeed1ba959e"},"schema_version":"1.0","source":{"id":"2311.02898","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02898","created_at":"2026-07-05T07:10:30Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02898v2","created_at":"2026-07-05T07:10:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02898","created_at":"2026-07-05T07:10:30Z"},{"alias_kind":"pith_short_12","alias_value":"FN7O74TUI4KP","created_at":"2026-07-05T07:10:30Z"},{"alias_kind":"pith_short_16","alias_value":"FN7O74TUI4KPAKC2","created_at":"2026-07-05T07:10:30Z"},{"alias_kind":"pith_short_8","alias_value":"FN7O74TU","created_at":"2026-07-05T07:10:30Z"}],"graph_snapshots":[{"event_id":"sha256:61937b01ea0304d2bc562e3b43c5f6dd9cb5649d67044a71b52f757522d031c6","target":"graph","created_at":"2026-07-05T07:10:30Z","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/2311.02898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic alignment constraints. The proposed model first generates aligned semantic tokens using the neural transducer, then synthesizes a speech sample from the semantic tokens using a non-autoregressive(NAR) speech generator. This decoupled framework alleviates the training complexity of TTS and allows each stage to focus on 1) linguistic and alignment modeling an","authors_text":"Byoung Jin Choi, Dongjune Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-06T06:13:39Z","title":"Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02898","kind":"arxiv","version":2},"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":"sha256:85249cb1a0e7ff6af9c2ea9d0e92c4cb91a0f9cd86c93fcb4753ee08dfabcaab","target":"record","created_at":"2026-07-05T07:10:30Z","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":"84f4b39fee304fd3b83883838f623ac1de755f3380bdabf76a4521e0f1fa67b1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-06T06:13:39Z","title_canon_sha256":"8d6c20cdb01745a9e24c7bffd136af3186429b11791502319ca8cfeed1ba959e"},"schema_version":"1.0","source":{"id":"2311.02898","kind":"arxiv","version":2}},"canonical_sha256":"2b7eeff2744714f0285ae3d6acc1feae147a56e1cd908e15dcdbf321639100bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b7eeff2744714f0285ae3d6acc1feae147a56e1cd908e15dcdbf321639100bf","first_computed_at":"2026-07-05T07:10:30.817767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:30.817767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T+8Tv8UyPWozpI45tDrQafrs8nnCaf+VvfwdW32NAMkjNlaYmG6DyQEslJDihUbMlp0TYO7hpZ4NUDR7Ks82Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:30.818257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02898","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85249cb1a0e7ff6af9c2ea9d0e92c4cb91a0f9cd86c93fcb4753ee08dfabcaab","sha256:61937b01ea0304d2bc562e3b43c5f6dd9cb5649d67044a71b52f757522d031c6"],"state_sha256":"835f93521aa8864f93deca9ee05f9b3582776baeb9a24313992db27bff87e857"}