{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FN7O74TUI4KPAKC24PLKZQP6VY","short_pith_number":"pith:FN7O74TU","schema_version":"1.0","canonical_sha256":"2b7eeff2744714f0285ae3d6acc1feae147a56e1cd908e15dcdbf321639100bf","source":{"kind":"arxiv","id":"2311.02898","version":2},"attestation_state":"computed","paper":{"title":"Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Dongjune Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim","submitted_at":"2023-11-06T06:13:39Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.02898","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-06T06:13:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d6c20cdb01745a9e24c7bffd136af3186429b11791502319ca8cfeed1ba959e","abstract_canon_sha256":"84f4b39fee304fd3b83883838f623ac1de755f3380bdabf76a4521e0f1fa67b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:30.818257Z","signature_b64":"T+8Tv8UyPWozpI45tDrQafrs8nnCaf+VvfwdW32NAMkjNlaYmG6DyQEslJDihUbMlp0TYO7hpZ4NUDR7Ks82Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b7eeff2744714f0285ae3d6acc1feae147a56e1cd908e15dcdbf321639100bf","last_reissued_at":"2026-07-05T07:10:30.817767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:30.817767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Dongjune Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim","submitted_at":"2023-11-06T06:13:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02898","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.02898/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.02898","created_at":"2026-07-05T07:10:30.817824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02898v2","created_at":"2026-07-05T07:10:30.817824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02898","created_at":"2026-07-05T07:10:30.817824+00:00"},{"alias_kind":"pith_short_12","alias_value":"FN7O74TUI4KP","created_at":"2026-07-05T07:10:30.817824+00:00"},{"alias_kind":"pith_short_16","alias_value":"FN7O74TUI4KPAKC2","created_at":"2026-07-05T07:10:30.817824+00:00"},{"alias_kind":"pith_short_8","alias_value":"FN7O74TU","created_at":"2026-07-05T07:10:30.817824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY","json":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY.json","graph_json":"https://pith.science/api/pith-number/FN7O74TUI4KPAKC24PLKZQP6VY/graph.json","events_json":"https://pith.science/api/pith-number/FN7O74TUI4KPAKC24PLKZQP6VY/events.json","paper":"https://pith.science/paper/FN7O74TU"},"agent_actions":{"view_html":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY","download_json":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY.json","view_paper":"https://pith.science/paper/FN7O74TU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02898&json=true","fetch_graph":"https://pith.science/api/pith-number/FN7O74TUI4KPAKC24PLKZQP6VY/graph.json","fetch_events":"https://pith.science/api/pith-number/FN7O74TUI4KPAKC24PLKZQP6VY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY/action/storage_attestation","attest_author":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY/action/author_attestation","sign_citation":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY/action/citation_signature","submit_replication":"https://pith.science/pith/FN7O74TUI4KPAKC24PLKZQP6VY/action/replication_record"}},"created_at":"2026-07-05T07:10:30.817824+00:00","updated_at":"2026-07-05T07:10:30.817824+00:00"}