{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BJNNHZKFMOHUDM76UFXHE36EFH","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":"9061f3262570df312335d4fa991134f51e77c435d9b748309a48b312d30ade7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-30T00:05:03Z","title_canon_sha256":"8317afa31f45e47426e5adb63744b7df08aac994c77d502b9c279cf6d07277d7"},"schema_version":"1.0","source":{"id":"2604.27273","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27273","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27273v2","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27273","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"BJNNHZKFMOHU","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"BJNNHZKFMOHUDM76","created_at":"2026-06-09T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"BJNNHZKF","created_at":"2026-06-09T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:c6376e8ae1b4fb51a067dc9aca2072f6e1681cfe96d2eb63120cbbc4a5ccc45f","target":"graph","created_at":"2026-06-09T01:04:43Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments demonstrate consistent word error rate (WER) reductions on real accented speech, including cross-speaker evaluation and ultra-low data regimes. A matched-rate random phoneme baseline shows that phoneme-space perturbation itself is a strong form of augmentation, while LLM-guided edits provide additional gains through accent-conditioned structure."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM-based phoneme editing, guided by fewer than ten reference utterances, reliably produces accent-conditioned pronunciations whose synthetic speech transfers to measurable improvements on real accented ASR test sets."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Few-shot TTS adaptation combined with LLM-guided phoneme editing produces synthetic accented speech that improves ASR word error rates on real accented audio even in cross-speaker and ultra-low-data settings."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Adapting TTS to an accent with under ten utterances and LLM phoneme edits produces synthetic data that reduces ASR word error rates on real accented speech."}],"snapshot_sha256":"fb145624292c262c98dd17bd7574132c8726198bd0f10af269111174862a03a3"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T22:40:44.099732Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:25:11.615394Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.27273/integrity.json","findings":[],"snapshot_sha256":"f792094dfca903e06ac8fb1355a90a6d22dbf84f6d0bcdffac1a18ca794813ce","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic accented speech is a promising way to improve automatic speech recognition (ASR) when real accented recordings are scarce. We ask what makes such data useful for ASR fine-tuning: target-accent phoneme edits that expose the recognizer to accent-specific pronunciations, or random phoneme perturbations that act as augmentation in phoneme space. In a few-shot TTS pipeline, we compare LLM-generated accent edits with matched-rate random substitutions and oracle controls using ground-truth accented phonemes and prosody. Random substitutions recover much of the ASR gain: LLM target-accent ed","authors_text":"Dilek Hakkani-T\\\"ur, Mark Hasegawa-Johnson, Nimet Beyza Bozdag, Volodymyr Kindratenko, Yurii Halychanskyi","cross_cats":[],"headline":"Adapting TTS to an accent with under ten utterances and LLM phoneme edits produces synthetic data that reduces ASR word error rates on real accented speech.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-30T00:05:03Z","title":"Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27273","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T09:01:57.698631Z","id":"73593e90-a4cf-4fbb-aa30-732bdac13838","model_set":{"reader":"grok-4.3"},"one_line_summary":"Few-shot TTS adaptation combined with LLM-guided phoneme editing produces synthetic accented speech that improves ASR word error rates on real accented audio even in cross-speaker and ultra-low-data settings.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Adapting TTS to an accent with under ten utterances and LLM phoneme edits produces synthetic data that reduces ASR word error rates on real accented speech.","strongest_claim":"Experiments demonstrate consistent word error rate (WER) reductions on real accented speech, including cross-speaker evaluation and ultra-low data regimes. A matched-rate random phoneme baseline shows that phoneme-space perturbation itself is a strong form of augmentation, while LLM-guided edits provide additional gains through accent-conditioned structure.","weakest_assumption":"That LLM-based phoneme editing, guided by fewer than ten reference utterances, reliably produces accent-conditioned pronunciations whose synthetic speech transfers to measurable improvements on real accented ASR test sets."}},"verdict_id":"73593e90-a4cf-4fbb-aa30-732bdac13838"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:08dcf80cd8d6601449200cd025f9851765475f940825631de67ab9edba94de34","target":"record","created_at":"2026-06-09T01:04:43Z","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":"9061f3262570df312335d4fa991134f51e77c435d9b748309a48b312d30ade7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-30T00:05:03Z","title_canon_sha256":"8317afa31f45e47426e5adb63744b7df08aac994c77d502b9c279cf6d07277d7"},"schema_version":"1.0","source":{"id":"2604.27273","kind":"arxiv","version":2}},"canonical_sha256":"0a5ad3e545638f41b3fea16e726fc429d5d08fc763d803e2b38bdf8f00cf7ee6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a5ad3e545638f41b3fea16e726fc429d5d08fc763d803e2b38bdf8f00cf7ee6","first_computed_at":"2026-06-09T01:04:43.174118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:43.174118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8zepYZhbfsVX20sAaBYUBQGXlQyZrv0QYpha4wGKmuSuhas8YJ7mk+D0Rh1wRowroqzv59n5TJnmxio/TIuPAQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:43.174546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27273","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08dcf80cd8d6601449200cd025f9851765475f940825631de67ab9edba94de34","sha256:c6376e8ae1b4fb51a067dc9aca2072f6e1681cfe96d2eb63120cbbc4a5ccc45f"],"state_sha256":"e96693d09a64721b5650546f3e1224747e0476e44ad6a52222e5626a84a01079"}