{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3IYPCVXOWZG6RM2KYZFLPVLNMC","short_pith_number":"pith:3IYPCVXO","canonical_record":{"source":{"id":"2406.17310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-25T06:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"0574151cf7c943dae8714d19982c01763b1f2ae7eedefd6a227d6ae298fdabda","abstract_canon_sha256":"0f4cc7e1a62c305c3307a678392e59c01645a7ddab8e0922f3d783a0a7008dd4"},"schema_version":"1.0"},"canonical_sha256":"da30f156eeb64de8b34ac64ab7d56d6083d8448657bd2726dc1b66a013b54efe","source":{"kind":"arxiv","id":"2406.17310","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17310","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17310v1","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17310","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_12","alias_value":"3IYPCVXOWZG6","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_16","alias_value":"3IYPCVXOWZG6RM2K","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_8","alias_value":"3IYPCVXO","created_at":"2026-07-05T08:36:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3IYPCVXOWZG6RM2KYZFLPVLNMC","target":"record","payload":{"canonical_record":{"source":{"id":"2406.17310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-25T06:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"0574151cf7c943dae8714d19982c01763b1f2ae7eedefd6a227d6ae298fdabda","abstract_canon_sha256":"0f4cc7e1a62c305c3307a678392e59c01645a7ddab8e0922f3d783a0a7008dd4"},"schema_version":"1.0"},"canonical_sha256":"da30f156eeb64de8b34ac64ab7d56d6083d8448657bd2726dc1b66a013b54efe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:32.578403Z","signature_b64":"/Z+AGZJv1eLxqErVnmHJtadeK+TfqbVDMzOEYBKSs9wKuFh/kSMJG6CMru5+qRxv9kJ04Kf+yoQ81Nyb94cUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da30f156eeb64de8b34ac64ab7d56d6083d8448657bd2726dc1b66a013b54efe","last_reissued_at":"2026-07-05T08:36:32.577973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:32.577973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.17310","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":"2026-07-05T08:36:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2gDHY+6Pp1b2+L6qPUXgHz795xuLukEAaiCxb4prgn6wQhpvC+ohsc2AIbjwT7Hi4oOF0TtD5jAyU/vtSh49CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:24:47.029448Z"},"content_sha256":"8e1b55ec5b7663b9b525deedb8a4b83a3a5aa244095ebbcac537fdd7d45f31c9","schema_version":"1.0","event_id":"sha256:8e1b55ec5b7663b9b525deedb8a4b83a3a5aa244095ebbcac537fdd7d45f31c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3IYPCVXOWZG6RM2KYZFLPVLNMC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hoon-Young Cho, Ji-Hyun Lee, Joun Yeop Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim","submitted_at":"2024-06-25T06:46:47Z","abstract_excerpt":"We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting module, which processes text and a speech prompt into semantic tokens focusing on linguistic contents and alignment, and the Speaking module, which captures the timbre of the target voice to generate acoustic tokens from semantic tokens, enriching speech reconstruction. The Interpreting stage employs a transducer for its robustness in aligning text to speech. In contrast, the Spea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17310","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/2406.17310/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":"2026-07-05T08:36:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o1Lf4tEy032hgMgFmdQamuJkBhvneiAMEIw8Od78hTntaBcmLhE4QFvXa5hiK9cO+oH2rRU7cMvhytl9xXYsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:24:47.030358Z"},"content_sha256":"e0d3faf94313a310e646bb6498fc86aeb8ffd22b3bc75746f0503ed80169d249","schema_version":"1.0","event_id":"sha256:e0d3faf94313a310e646bb6498fc86aeb8ffd22b3bc75746f0503ed80169d249"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IYPCVXOWZG6RM2KYZFLPVLNMC/bundle.json","state_url":"https://pith.science/pith/3IYPCVXOWZG6RM2KYZFLPVLNMC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IYPCVXOWZG6RM2KYZFLPVLNMC/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":"2026-08-08T20:24:47Z","links":{"resolver":"https://pith.science/pith/3IYPCVXOWZG6RM2KYZFLPVLNMC","bundle":"https://pith.science/pith/3IYPCVXOWZG6RM2KYZFLPVLNMC/bundle.json","state":"https://pith.science/pith/3IYPCVXOWZG6RM2KYZFLPVLNMC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IYPCVXOWZG6RM2KYZFLPVLNMC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3IYPCVXOWZG6RM2KYZFLPVLNMC","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":"0f4cc7e1a62c305c3307a678392e59c01645a7ddab8e0922f3d783a0a7008dd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-25T06:46:47Z","title_canon_sha256":"0574151cf7c943dae8714d19982c01763b1f2ae7eedefd6a227d6ae298fdabda"},"schema_version":"1.0","source":{"id":"2406.17310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17310","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17310v1","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17310","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_12","alias_value":"3IYPCVXOWZG6","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_16","alias_value":"3IYPCVXOWZG6RM2K","created_at":"2026-07-05T08:36:32Z"},{"alias_kind":"pith_short_8","alias_value":"3IYPCVXO","created_at":"2026-07-05T08:36:32Z"}],"graph_snapshots":[{"event_id":"sha256:e0d3faf94313a310e646bb6498fc86aeb8ffd22b3bc75746f0503ed80169d249","target":"graph","created_at":"2026-07-05T08:36:32Z","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/2406.17310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting module, which processes text and a speech prompt into semantic tokens focusing on linguistic contents and alignment, and the Speaking module, which captures the timbre of the target voice to generate acoustic tokens from semantic tokens, enriching speech reconstruction. The Interpreting stage employs a transducer for its robustness in aligning text to speech. In contrast, the Spea","authors_text":"Hoon-Young Cho, Ji-Hyun Lee, Joun Yeop Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-25T06:46:47Z","title":"High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17310","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":"sha256:8e1b55ec5b7663b9b525deedb8a4b83a3a5aa244095ebbcac537fdd7d45f31c9","target":"record","created_at":"2026-07-05T08:36:32Z","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":"0f4cc7e1a62c305c3307a678392e59c01645a7ddab8e0922f3d783a0a7008dd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-25T06:46:47Z","title_canon_sha256":"0574151cf7c943dae8714d19982c01763b1f2ae7eedefd6a227d6ae298fdabda"},"schema_version":"1.0","source":{"id":"2406.17310","kind":"arxiv","version":1}},"canonical_sha256":"da30f156eeb64de8b34ac64ab7d56d6083d8448657bd2726dc1b66a013b54efe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da30f156eeb64de8b34ac64ab7d56d6083d8448657bd2726dc1b66a013b54efe","first_computed_at":"2026-07-05T08:36:32.577973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:32.577973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Z+AGZJv1eLxqErVnmHJtadeK+TfqbVDMzOEYBKSs9wKuFh/kSMJG6CMru5+qRxv9kJ04Kf+yoQ81Nyb94cUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:32.578403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1b55ec5b7663b9b525deedb8a4b83a3a5aa244095ebbcac537fdd7d45f31c9","sha256:e0d3faf94313a310e646bb6498fc86aeb8ffd22b3bc75746f0503ed80169d249"],"state_sha256":"804a0c411a933c46920d33158a364c98faceae71911419a9ad229cc805d38c79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8dPb0b4yXK/vTEhbydkyzgcrXPWLDdoFQE1YNdzFGMryFzXY047rivd51pvY1n9X5tSv1haDxH9dnP+uL/L1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:24:47.043557Z","bundle_sha256":"ca459265c43f4b68d3d7ce22e8de43700520f5daaa5e2e48911773b40d93718d"}}