{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IVYUG446HVDI3J4WRSL2MPJZA3","short_pith_number":"pith:IVYUG446","canonical_record":{"source":{"id":"2401.01498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-01-03T02:03:36Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"b63cc8b8cbc2d1e20e7344d85ade3df7dc423a1ccd667bc5a29c85aea6f1cce1","abstract_canon_sha256":"24ed2cef74dcdcdb50e76b0c5a4da4954c2981615c600a63fe61970cfa19bea0"},"schema_version":"1.0"},"canonical_sha256":"457143739e3d468da7968c97a63d3906d00557c43663f7acf88d71db6a900799","source":{"kind":"arxiv","id":"2401.01498","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IVYUG446HVDI3J4WRSL2MPJZA3","target":"record","payload":{"canonical_record":{"source":{"id":"2401.01498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-01-03T02:03:36Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"b63cc8b8cbc2d1e20e7344d85ade3df7dc423a1ccd667bc5a29c85aea6f1cce1","abstract_canon_sha256":"24ed2cef74dcdcdb50e76b0c5a4da4954c2981615c600a63fe61970cfa19bea0"},"schema_version":"1.0"},"canonical_sha256":"457143739e3d468da7968c97a63d3906d00557c43663f7acf88d71db6a900799","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:38.224493Z","signature_b64":"v86emoi+fLOygntHMgyZ6ksyOscZszg3p8uTDybq8Tf9DH/mIZ9SbjR80usfNjpLvKPB0rybldQDCjttavVvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457143739e3d468da7968c97a63d3906d00557c43663f7acf88d71db6a900799","last_reissued_at":"2026-07-05T09:25:38.224028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:38.224028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.01498","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:25:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bsi5GgpA36fmXLqd0ygG8xat6ETmXn746JRrP3N7YoqX5v81n9MNGsGKzAdYR3m7eC+43FS9jKLZ3HviMT+tAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:21:07.196429Z"},"content_sha256":"bb3716f5e612145cbea85538ae47b7669295bc9e8e44c786a335041572c43ce8","schema_version":"1.0","event_id":"sha256:bb3716f5e612145cbea85538ae47b7669295bc9e8e44c786a335041572c43ce8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IVYUG446HVDI3J4WRSL2MPJZA3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Joun Yeop Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Semin Kim","submitted_at":"2024-01-03T02:03:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01498","kind":"arxiv","version":1},"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/2401.01498/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:25:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lb1ptzEPzcnea37IIicKEWHSK0zQiPQE0gWUcaajYC2t5fsLLB06mQtRKsJQvjAvwCqjA7cTK4MBdSjR/dsBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:21:07.200277Z"},"content_sha256":"ab5450b44c82985b1abc3f866d2d7e8ba58b0eb36331df34068a05c128d9e43b","schema_version":"1.0","event_id":"sha256:ab5450b44c82985b1abc3f866d2d7e8ba58b0eb36331df34068a05c128d9e43b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVYUG446HVDI3J4WRSL2MPJZA3/bundle.json","state_url":"https://pith.science/pith/IVYUG446HVDI3J4WRSL2MPJZA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVYUG446HVDI3J4WRSL2MPJZA3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T02:21:07Z","links":{"resolver":"https://pith.science/pith/IVYUG446HVDI3J4WRSL2MPJZA3","bundle":"https://pith.science/pith/IVYUG446HVDI3J4WRSL2MPJZA3/bundle.json","state":"https://pith.science/pith/IVYUG446HVDI3J4WRSL2MPJZA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVYUG446HVDI3J4WRSL2MPJZA3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a2/TsQXODRVj/6tqfjzMRtMULkY3sfLLSEXwfqevc47AssLLmSjdLUi2fI2N9bD6MFXKFNc69Koc5tkfWAXhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:21:07.217891Z","bundle_sha256":"930e85943c0ac9627eff43c328975260af621877c7853cafc4cf7675e7f432b0"}}