{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5PO7MT5ER7UGNNBVYW5GGCZPJ7","short_pith_number":"pith:5PO7MT5E","canonical_record":{"source":{"id":"2210.14850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T16:49:57Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8541ecf4e149d72cae9c8e028d84edbe7db32c170e03b89482cab43339f0a0f5","abstract_canon_sha256":"de417cce84427bec3d0fa7cdccf3cc00f1681b54707d3b2d220969b1f6120bf8"},"schema_version":"1.0"},"canonical_sha256":"ebddf64fa48fe866b435c5ba630b2f4fd9dbdd3978143acf6830ece15f6502be","source":{"kind":"arxiv","id":"2210.14850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14850","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14850v1","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14850","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"5PO7MT5ER7UG","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"5PO7MT5ER7UGNNBV","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"5PO7MT5E","created_at":"2026-07-05T05:10:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5PO7MT5ER7UGNNBVYW5GGCZPJ7","target":"record","payload":{"canonical_record":{"source":{"id":"2210.14850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T16:49:57Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8541ecf4e149d72cae9c8e028d84edbe7db32c170e03b89482cab43339f0a0f5","abstract_canon_sha256":"de417cce84427bec3d0fa7cdccf3cc00f1681b54707d3b2d220969b1f6120bf8"},"schema_version":"1.0"},"canonical_sha256":"ebddf64fa48fe866b435c5ba630b2f4fd9dbdd3978143acf6830ece15f6502be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:50.292501Z","signature_b64":"2eIMq7JsH2iWkzjbu7OVEhCOnkX6xguxk3r5BgPU++PMdrDqoRYrahwdrgDlYL0fB/vlEaDPLdlBqgYsr6PHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebddf64fa48fe866b435c5ba630b2f4fd9dbdd3978143acf6830ece15f6502be","last_reissued_at":"2026-07-05T05:10:50.291786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:50.291786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.14850","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":"2026-07-05T05:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mgMykY8AcYRmuyWPEdydcVJEM5wsJ581E3e3wJVWyhpXPjKHREHKk+2iLEumb5Eh+t4APNf/t5ZelJdVUf8pAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T07:42:33.265352Z"},"content_sha256":"b36cb1119d7be74fffd01c6800bfda88daa89bf464a26d420973f04cbc7c6859","schema_version":"1.0","event_id":"sha256:b36cb1119d7be74fffd01c6800bfda88daa89bf464a26d420973f04cbc7c6859"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5PO7MT5ER7UGNNBVYW5GGCZPJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki","submitted_at":"2022-10-26T16:49:57Z","abstract_excerpt":"This paper proposes a method for selecting training data for text-to-speech (TTS) synthesis from dark data. TTS models are typically trained on high-quality speech corpora that cost much time and money for data collection, which makes it very challenging to increase speaker variation. In contrast, there is a large amount of data whose availability is unknown (a.k.a, \"dark data\"), such as YouTube videos. To utilize data other than TTS corpora, previous studies have selected speech data from the corpora on the basis of acoustic quality. However, considering that TTS models robust to data noise h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14850","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/2210.14850/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":"2026-07-05T05:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJhwipnsYQkZLbxQ+0om0AelCUlX8HdMZ1YUb0s/RdI8ghhCZtjqIiYkdh/wJaiOn8sxDRiQLXT5pbbudYMSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T07:42:33.265719Z"},"content_sha256":"dab74a3b153ecdda02fd5b02ada6b480e7a8156c5cf91d65fc11878044da5cd8","schema_version":"1.0","event_id":"sha256:dab74a3b153ecdda02fd5b02ada6b480e7a8156c5cf91d65fc11878044da5cd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PO7MT5ER7UGNNBVYW5GGCZPJ7/bundle.json","state_url":"https://pith.science/pith/5PO7MT5ER7UGNNBVYW5GGCZPJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PO7MT5ER7UGNNBVYW5GGCZPJ7/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":"2026-07-18T07:42:33Z","links":{"resolver":"https://pith.science/pith/5PO7MT5ER7UGNNBVYW5GGCZPJ7","bundle":"https://pith.science/pith/5PO7MT5ER7UGNNBVYW5GGCZPJ7/bundle.json","state":"https://pith.science/pith/5PO7MT5ER7UGNNBVYW5GGCZPJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PO7MT5ER7UGNNBVYW5GGCZPJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5PO7MT5ER7UGNNBVYW5GGCZPJ7","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":"de417cce84427bec3d0fa7cdccf3cc00f1681b54707d3b2d220969b1f6120bf8","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T16:49:57Z","title_canon_sha256":"8541ecf4e149d72cae9c8e028d84edbe7db32c170e03b89482cab43339f0a0f5"},"schema_version":"1.0","source":{"id":"2210.14850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14850","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14850v1","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14850","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"5PO7MT5ER7UG","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"5PO7MT5ER7UGNNBV","created_at":"2026-07-05T05:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"5PO7MT5E","created_at":"2026-07-05T05:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:dab74a3b153ecdda02fd5b02ada6b480e7a8156c5cf91d65fc11878044da5cd8","target":"graph","created_at":"2026-07-05T05:10:50Z","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/2210.14850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a method for selecting training data for text-to-speech (TTS) synthesis from dark data. TTS models are typically trained on high-quality speech corpora that cost much time and money for data collection, which makes it very challenging to increase speaker variation. In contrast, there is a large amount of data whose availability is unknown (a.k.a, \"dark data\"), such as YouTube videos. To utilize data other than TTS corpora, previous studies have selected speech data from the corpora on the basis of acoustic quality. However, considering that TTS models robust to data noise h","authors_text":"Hiroshi Saruwatari, Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T16:49:57Z","title":"Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14850","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:b36cb1119d7be74fffd01c6800bfda88daa89bf464a26d420973f04cbc7c6859","target":"record","created_at":"2026-07-05T05:10:50Z","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":"de417cce84427bec3d0fa7cdccf3cc00f1681b54707d3b2d220969b1f6120bf8","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T16:49:57Z","title_canon_sha256":"8541ecf4e149d72cae9c8e028d84edbe7db32c170e03b89482cab43339f0a0f5"},"schema_version":"1.0","source":{"id":"2210.14850","kind":"arxiv","version":1}},"canonical_sha256":"ebddf64fa48fe866b435c5ba630b2f4fd9dbdd3978143acf6830ece15f6502be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebddf64fa48fe866b435c5ba630b2f4fd9dbdd3978143acf6830ece15f6502be","first_computed_at":"2026-07-05T05:10:50.291786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:50.291786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2eIMq7JsH2iWkzjbu7OVEhCOnkX6xguxk3r5BgPU++PMdrDqoRYrahwdrgDlYL0fB/vlEaDPLdlBqgYsr6PHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:50.292501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b36cb1119d7be74fffd01c6800bfda88daa89bf464a26d420973f04cbc7c6859","sha256:dab74a3b153ecdda02fd5b02ada6b480e7a8156c5cf91d65fc11878044da5cd8"],"state_sha256":"d39fe65ad86d34c9277aa7c12bada03cd2f219109501107f0c21fa042404f8dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCYouzKq0aBNZb6WaUan+l7YSZ8HFssGiZ4cxqNuyIOhOO6I5hQFGj7nFCdeyiaABEKuuTy6FgEDQ1P7DOwyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T07:42:33.268308Z","bundle_sha256":"764e97094d30d55d5b3bdba2f450532467bec09a9c9a4d50822832cd29b47ea5"}}