{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LBBNJN3FG3LUTPBNVIBDK7FMEQ","short_pith_number":"pith:LBBNJN3F","canonical_record":{"source":{"id":"2506.11130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T17:30:32Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"44e5b81ff8a573b1fb9aeb6b70597a89ba8c2ea19a227659033ad1cbb007021c","abstract_canon_sha256":"61f83d6c933f54c13a523770fb51a4f49c625a86bba6245f4b8bda3174802e30"},"schema_version":"1.0"},"canonical_sha256":"5842d4b76536d749bc2daa02357cac240bd1ad9054825edfc4b1baaddeab11b2","source":{"kind":"arxiv","id":"2506.11130","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11130","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11130v2","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11130","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"pith_short_12","alias_value":"LBBNJN3FG3LU","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"pith_short_16","alias_value":"LBBNJN3FG3LUTPBN","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"pith_short_8","alias_value":"LBBNJN3F","created_at":"2026-07-05T11:22:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LBBNJN3FG3LUTPBNVIBDK7FMEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T17:30:32Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"44e5b81ff8a573b1fb9aeb6b70597a89ba8c2ea19a227659033ad1cbb007021c","abstract_canon_sha256":"61f83d6c933f54c13a523770fb51a4f49c625a86bba6245f4b8bda3174802e30"},"schema_version":"1.0"},"canonical_sha256":"5842d4b76536d749bc2daa02357cac240bd1ad9054825edfc4b1baaddeab11b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:19.098881Z","signature_b64":"yg4VXrpsIZVxIHTfnxV0GbTkfQh4Lo+cgXVG3WcXpWk0PBp4pUJ1EU9uoiBI1+1MqRe2ru7b0qQk2gfcFBkqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5842d4b76536d749bc2daa02357cac240bd1ad9054825edfc4b1baaddeab11b2","last_reissued_at":"2026-07-05T11:22:19.098372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:19.098372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11130","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PZKrUTTjL94X155GBMirB9Z1QcWRqyDoSIqgTDWahHd/hqNJ4njsgZQVd5JG9Ka5crfiC7JEW0GIM30w4o0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T05:59:09.412873Z"},"content_sha256":"fbb97ebae24eae4741fb28bc3746215fbeb18dc560bc3c8978f86fcb16ae5161","schema_version":"1.0","event_id":"sha256:fbb97ebae24eae4741fb28bc3746215fbeb18dc560bc3c8978f86fcb16ae5161"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LBBNJN3FG3LUTPBNVIBDK7FMEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chan-Jan Hsu, Cheng-Kang Chou, Ho-Lam Chung, Hsi-Chun Cheng, Hung-yi Lee, Kuan Po Huang, Liang-Hsuan Tseng, Yu-Kuan Fu","submitted_at":"2025-06-10T17:30:32Z","abstract_excerpt":"We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity text-to-speech (TTS) system. Then, synthesized speech text pairs are bootstrapped into the original ASR system, completing the closed-loop self-improvement cycle. We demonstrated the effectiveness of the framework on Taiwanese Mandarin speech. Leveraging 6,000 hours of unlabeled speech, a moderate amount of text data, and synthetic content from the AI models, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11130","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/2506.11130/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":"2026-07-05T11:22:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aTCmoyGPNlTQw6y+mkbPfaJdYhuQAYJgxsvn0xKH5Li/Cuo5Yd+wpyXL09m7MStbmjmjT35WYb+eh2a+TkuZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T05:59:09.413261Z"},"content_sha256":"df17b3aa41090367324b626aec506961e0692e0fe8f82bc2bf9a6f8953aa41b8","schema_version":"1.0","event_id":"sha256:df17b3aa41090367324b626aec506961e0692e0fe8f82bc2bf9a6f8953aa41b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBBNJN3FG3LUTPBNVIBDK7FMEQ/bundle.json","state_url":"https://pith.science/pith/LBBNJN3FG3LUTPBNVIBDK7FMEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBBNJN3FG3LUTPBNVIBDK7FMEQ/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":"2026-07-18T05:59:09Z","links":{"resolver":"https://pith.science/pith/LBBNJN3FG3LUTPBNVIBDK7FMEQ","bundle":"https://pith.science/pith/LBBNJN3FG3LUTPBNVIBDK7FMEQ/bundle.json","state":"https://pith.science/pith/LBBNJN3FG3LUTPBNVIBDK7FMEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBBNJN3FG3LUTPBNVIBDK7FMEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LBBNJN3FG3LUTPBNVIBDK7FMEQ","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":"61f83d6c933f54c13a523770fb51a4f49c625a86bba6245f4b8bda3174802e30","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T17:30:32Z","title_canon_sha256":"44e5b81ff8a573b1fb9aeb6b70597a89ba8c2ea19a227659033ad1cbb007021c"},"schema_version":"1.0","source":{"id":"2506.11130","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11130","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11130v2","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11130","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"pith_short_12","alias_value":"LBBNJN3FG3LU","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"pith_short_16","alias_value":"LBBNJN3FG3LUTPBN","created_at":"2026-07-05T11:22:19Z"},{"alias_kind":"pith_short_8","alias_value":"LBBNJN3F","created_at":"2026-07-05T11:22:19Z"}],"graph_snapshots":[{"event_id":"sha256:df17b3aa41090367324b626aec506961e0692e0fe8f82bc2bf9a6f8953aa41b8","target":"graph","created_at":"2026-07-05T11:22:19Z","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/2506.11130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity text-to-speech (TTS) system. Then, synthesized speech text pairs are bootstrapped into the original ASR system, completing the closed-loop self-improvement cycle. We demonstrated the effectiveness of the framework on Taiwanese Mandarin speech. Leveraging 6,000 hours of unlabeled speech, a moderate amount of text data, and synthetic content from the AI models, we","authors_text":"Chan-Jan Hsu, Cheng-Kang Chou, Ho-Lam Chung, Hsi-Chun Cheng, Hung-yi Lee, Kuan Po Huang, Liang-Hsuan Tseng, Yu-Kuan Fu","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T17:30:32Z","title":"A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11130","kind":"arxiv","version":2},"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:fbb97ebae24eae4741fb28bc3746215fbeb18dc560bc3c8978f86fcb16ae5161","target":"record","created_at":"2026-07-05T11:22:19Z","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":"61f83d6c933f54c13a523770fb51a4f49c625a86bba6245f4b8bda3174802e30","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T17:30:32Z","title_canon_sha256":"44e5b81ff8a573b1fb9aeb6b70597a89ba8c2ea19a227659033ad1cbb007021c"},"schema_version":"1.0","source":{"id":"2506.11130","kind":"arxiv","version":2}},"canonical_sha256":"5842d4b76536d749bc2daa02357cac240bd1ad9054825edfc4b1baaddeab11b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5842d4b76536d749bc2daa02357cac240bd1ad9054825edfc4b1baaddeab11b2","first_computed_at":"2026-07-05T11:22:19.098372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:19.098372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yg4VXrpsIZVxIHTfnxV0GbTkfQh4Lo+cgXVG3WcXpWk0PBp4pUJ1EU9uoiBI1+1MqRe2ru7b0qQk2gfcFBkqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:19.098881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11130","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbb97ebae24eae4741fb28bc3746215fbeb18dc560bc3c8978f86fcb16ae5161","sha256:df17b3aa41090367324b626aec506961e0692e0fe8f82bc2bf9a6f8953aa41b8"],"state_sha256":"c475e398c79f7605525f2a92eb3ecf0e892d611877f6ee3943d1196f673aba41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ynpAFxOWTylc59rFDZKz/P+f1mXb+v8gNAfsPmx3RufWsWlt9gmikuwFX1x3DAch5rWGeEeCAixCBmNlE+6pCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T05:59:09.415404Z","bundle_sha256":"3b24d47daa4aafcf3976bef87e98a94672996cdedfc3f31f7dc6bdc6f1a67d9a"}}