{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FVIFMNPGB5MZHURKTA5FB4JSAU","short_pith_number":"pith:FVIFMNPG","canonical_record":{"source":{"id":"2412.03074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T06:52:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"82d55b5c266697cfb69098f023a328f894461cd3d4153ab9d415b69733609d51","abstract_canon_sha256":"148057d6a0f2f067129898620b13da0e857d3903a3f1e29bceef249abc31366b"},"schema_version":"1.0"},"canonical_sha256":"2d505635e60f5993d22a983a50f132053febd3d5c808a2cd0d0f3bf1c4bf17af","source":{"kind":"arxiv","id":"2412.03074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03074","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03074v1","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03074","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"FVIFMNPGB5MZ","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"pith_short_16","alias_value":"FVIFMNPGB5MZHURK","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"pith_short_8","alias_value":"FVIFMNPG","created_at":"2026-07-05T09:44:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FVIFMNPGB5MZHURKTA5FB4JSAU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T06:52:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"82d55b5c266697cfb69098f023a328f894461cd3d4153ab9d415b69733609d51","abstract_canon_sha256":"148057d6a0f2f067129898620b13da0e857d3903a3f1e29bceef249abc31366b"},"schema_version":"1.0"},"canonical_sha256":"2d505635e60f5993d22a983a50f132053febd3d5c808a2cd0d0f3bf1c4bf17af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:24.617744Z","signature_b64":"B/9lApZ3XepMvV5Qlk4e9lNXH8WH1aQFB9IBpU85/dtG5GoyjPoK/2tOn4+fDvWeSpcJFqeV4dMObuXjVwtzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d505635e60f5993d22a983a50f132053febd3d5c808a2cd0d0f3bf1c4bf17af","last_reissued_at":"2026-07-05T09:44:24.617349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:24.617349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03074","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":"2026-07-05T09:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/NTFe9IPjdjEC7+ET1k9TNCJdix/EmNXY6QRiYiFie+kckyO4njwXbpDUUXheIZ1d0XaNR9uEC2G2XOm9dDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:27:41.395313Z"},"content_sha256":"61a1adbe6deba739eb235b549653f8793ba92c07a5d2c362e145bf37e97ec4c1","schema_version":"1.0","event_id":"sha256:61a1adbe6deba739eb235b549653f8793ba92c07a5d2c362e145bf37e97ec4c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FVIFMNPGB5MZHURKTA5FB4JSAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daisuke Saito, Joonyong Park, Nobuaki Minematsu","submitted_at":"2024-12-04T06:52:03Z","abstract_excerpt":"We examine the text-free speech representations of raw audio obtained from a self-supervised learning (SSL) model by analyzing the synthesized speech using the SSL representations instead of conventional text representations. Since raw audio does not have paired speech representations as transcribed texts do, obtaining speech representations from unpaired speech is crucial for augmenting available datasets for speech synthesis. Specifically, the proposed speech synthesis is conducted using discrete symbol representations from the SSL model in comparison with text representations, and analytica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03074","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/2412.03074/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":"2026-07-05T09:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aZ2HFfSnD2QzQTDBO746CGmC59B6B39r5X7aa8myg07bL1zgEWoW7/lkyKFO0H6xSS8xOhbIovKZDKOHXKK8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:27:41.395891Z"},"content_sha256":"6df9ccd357291f54419efdeb0fa9d0ff487d9966970c9ea3891769ec04874a96","schema_version":"1.0","event_id":"sha256:6df9ccd357291f54419efdeb0fa9d0ff487d9966970c9ea3891769ec04874a96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FVIFMNPGB5MZHURKTA5FB4JSAU/bundle.json","state_url":"https://pith.science/pith/FVIFMNPGB5MZHURKTA5FB4JSAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FVIFMNPGB5MZHURKTA5FB4JSAU/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":"2026-08-15T08:27:41Z","links":{"resolver":"https://pith.science/pith/FVIFMNPGB5MZHURKTA5FB4JSAU","bundle":"https://pith.science/pith/FVIFMNPGB5MZHURKTA5FB4JSAU/bundle.json","state":"https://pith.science/pith/FVIFMNPGB5MZHURKTA5FB4JSAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FVIFMNPGB5MZHURKTA5FB4JSAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FVIFMNPGB5MZHURKTA5FB4JSAU","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":"148057d6a0f2f067129898620b13da0e857d3903a3f1e29bceef249abc31366b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T06:52:03Z","title_canon_sha256":"82d55b5c266697cfb69098f023a328f894461cd3d4153ab9d415b69733609d51"},"schema_version":"1.0","source":{"id":"2412.03074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03074","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03074v1","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03074","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"FVIFMNPGB5MZ","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"pith_short_16","alias_value":"FVIFMNPGB5MZHURK","created_at":"2026-07-05T09:44:24Z"},{"alias_kind":"pith_short_8","alias_value":"FVIFMNPG","created_at":"2026-07-05T09:44:24Z"}],"graph_snapshots":[{"event_id":"sha256:6df9ccd357291f54419efdeb0fa9d0ff487d9966970c9ea3891769ec04874a96","target":"graph","created_at":"2026-07-05T09:44:24Z","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/2412.03074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We examine the text-free speech representations of raw audio obtained from a self-supervised learning (SSL) model by analyzing the synthesized speech using the SSL representations instead of conventional text representations. Since raw audio does not have paired speech representations as transcribed texts do, obtaining speech representations from unpaired speech is crucial for augmenting available datasets for speech synthesis. Specifically, the proposed speech synthesis is conducted using discrete symbol representations from the SSL model in comparison with text representations, and analytica","authors_text":"Daisuke Saito, Joonyong Park, Nobuaki Minematsu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T06:52:03Z","title":"Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03074","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":"sha256:61a1adbe6deba739eb235b549653f8793ba92c07a5d2c362e145bf37e97ec4c1","target":"record","created_at":"2026-07-05T09:44:24Z","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":"148057d6a0f2f067129898620b13da0e857d3903a3f1e29bceef249abc31366b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T06:52:03Z","title_canon_sha256":"82d55b5c266697cfb69098f023a328f894461cd3d4153ab9d415b69733609d51"},"schema_version":"1.0","source":{"id":"2412.03074","kind":"arxiv","version":1}},"canonical_sha256":"2d505635e60f5993d22a983a50f132053febd3d5c808a2cd0d0f3bf1c4bf17af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d505635e60f5993d22a983a50f132053febd3d5c808a2cd0d0f3bf1c4bf17af","first_computed_at":"2026-07-05T09:44:24.617349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:24.617349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B/9lApZ3XepMvV5Qlk4e9lNXH8WH1aQFB9IBpU85/dtG5GoyjPoK/2tOn4+fDvWeSpcJFqeV4dMObuXjVwtzAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:24.617744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61a1adbe6deba739eb235b549653f8793ba92c07a5d2c362e145bf37e97ec4c1","sha256:6df9ccd357291f54419efdeb0fa9d0ff487d9966970c9ea3891769ec04874a96"],"state_sha256":"b53a11954b7061200cefc2a332b66b4f2868b51d976ea2378c7ac2db27e047bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cEWGN66Sjiy4LNJwYUYG9SATenWeqVAgzeDM9922bd47xoh0BkOb7sEXKteGNGHPBZ+sKeKVNVHtqZKMKYfrAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T08:27:41.399020Z","bundle_sha256":"9e9f68b45d5f8c7d6a0ba1e4a4e717dadb8448e75094c0c030e29811fd7f514b"}}