{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BJNNHZKFMOHUDM76UFXHE36EFH","short_pith_number":"pith:BJNNHZKF","schema_version":"1.0","canonical_sha256":"0a5ad3e545638f41b3fea16e726fc429d5d08fc763d803e2b38bdf8f00cf7ee6","source":{"kind":"arxiv","id":"2604.27273","version":2},"attestation_state":"computed","paper":{"title":"Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","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.","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Dilek Hakkani-T\\\"ur, Mark Hasegawa-Johnson, Nimet Beyza Bozdag, Volodymyr Kindratenko, Yurii Halychanskyi","submitted_at":"2026-04-30T00:05:03Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.27273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-30T00:05:03Z","cross_cats_sorted":[],"title_canon_sha256":"8317afa31f45e47426e5adb63744b7df08aac994c77d502b9c279cf6d07277d7","abstract_canon_sha256":"9061f3262570df312335d4fa991134f51e77c435d9b748309a48b312d30ade7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:43.174546Z","signature_b64":"8zepYZhbfsVX20sAaBYUBQGXlQyZrv0QYpha4wGKmuSuhas8YJ7mk+D0Rh1wRowroqzv59n5TJnmxio/TIuPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a5ad3e545638f41b3fea16e726fc429d5d08fc763d803e2b38bdf8f00cf7ee6","last_reissued_at":"2026-06-09T01:04:43.174118Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:43.174118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","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.","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Dilek Hakkani-T\\\"ur, Mark Hasegawa-Johnson, Nimet Beyza Bozdag, Volodymyr Kindratenko, Yurii Halychanskyi","submitted_at":"2026-04-30T00:05:03Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","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.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fb145624292c262c98dd17bd7574132c8726198bd0f10af269111174862a03a3"},"source":{"id":"2604.27273","kind":"arxiv","version":2},"verdict":{"id":"73593e90-a4cf-4fbb-aa30-732bdac13838","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T09:01:57.698631Z","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.","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","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.","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."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.27273/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"f792094dfca903e06ac8fb1355a90a6d22dbf84f6d0bcdffac1a18ca794813ce"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.27273","created_at":"2026-06-09T01:04:43.174172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.27273v2","created_at":"2026-06-09T01:04:43.174172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27273","created_at":"2026-06-09T01:04:43.174172+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJNNHZKFMOHU","created_at":"2026-06-09T01:04:43.174172+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJNNHZKFMOHUDM76","created_at":"2026-06-09T01:04:43.174172+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJNNHZKF","created_at":"2026-06-09T01:04:43.174172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.16417","citing_title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27273","citing_title":"Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH","json":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH.json","graph_json":"https://pith.science/api/pith-number/BJNNHZKFMOHUDM76UFXHE36EFH/graph.json","events_json":"https://pith.science/api/pith-number/BJNNHZKFMOHUDM76UFXHE36EFH/events.json","paper":"https://pith.science/paper/BJNNHZKF"},"agent_actions":{"view_html":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH","download_json":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH.json","view_paper":"https://pith.science/paper/BJNNHZKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.27273&json=true","fetch_graph":"https://pith.science/api/pith-number/BJNNHZKFMOHUDM76UFXHE36EFH/graph.json","fetch_events":"https://pith.science/api/pith-number/BJNNHZKFMOHUDM76UFXHE36EFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH/action/storage_attestation","attest_author":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH/action/author_attestation","sign_citation":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH/action/citation_signature","submit_replication":"https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH/action/replication_record"}},"created_at":"2026-06-09T01:04:43.174172+00:00","updated_at":"2026-06-09T01:04:43.174172+00:00"}