Pith Number

pith:BJNNHZKF

pith:2026:BJNNHZKFMOHUDM76UFXHE36EFH

not attested not anchored not stored refs pending

Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?

Dilek Hakkani-T\"ur, Mark Hasegawa-Johnson, Nimet Beyza Bozdag, Volodymyr Kindratenko, Yurii Halychanskyi

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.

arxiv:2604.27273 v2 · 2026-04-30 · cs.SD

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BJNNHZKFMOHUDM76UFXHE36EFH}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest 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.

C2weakest 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.

C3one 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.

Cited by

2 papers in Pith

Joycent: Diffusion-based Accent TTS without Accented Phone Prediction

Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?

Receipt and verification

First computed	2026-06-09T01:04:43.174118Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0a5ad3e545638f41b3fea16e726fc429d5d08fc763d803e2b38bdf8f00cf7ee6

Aliases

arxiv: 2604.27273 · arxiv_version: 2604.27273v2 · doi: 10.48550/arxiv.2604.27273 · pith_short_12: BJNNHZKFMOHU · pith_short_16: BJNNHZKFMOHUDM76 · pith_short_8: BJNNHZKF

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/BJNNHZKFMOHUDM76UFXHE36EFH \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0a5ad3e545638f41b3fea16e726fc429d5d08fc763d803e2b38bdf8f00cf7ee6

Canonical record JSON

{
  "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
  }
}