Pith Number

pith:X4QF3WZE

pith:2026:X4QF3WZE5PVMUC5NWNIJSDN6HZ

not attested not anchored not stored refs resolved

Refining Pseudo-Audio Prompts with Speech-Text Alignment for Text-Only Domain Adaptation in LLM-Based ASR

Ryo Magoshi, Takashi Maekaku, Yusuke Shinohara

A speech-text alignment method generates expressive pseudo-audio prompts for effective text-only domain adaptation in LLM-based ASR, outperforming prior text-only approaches on error rates and OOV coverage.

arxiv:2605.14340 v1 · 2026-05-14 · 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{X4QF3WZE5PVMUC5NWNIJSDN6HZ}

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

Our method efficiently generates highly expressive pseudo-audio prompts that bridges the modality gap, enabling effective target-domain adaptation. Experiments demonstrate that our approach outperforms existing text-only methods, improving both overall error rates and out-of-vocabulary coverage.

C2weakest assumption

That explicitly modeling speech-text alignment during pseudo-audio prompt generation will produce prompts expressive enough to close the modality gap and yield measurable gains in target-domain ASR without any real audio from that domain.

C3one line summary

References

38 extracted · 38 resolved · 3 Pith anchors

[1] As illustrated in Fig- ure 1, these architectures typically input representations from a pre-trained audio encoder into a trainable projector

[2] Refining Pseudo-Audio Prompts with Speech-Text Alignment for Text-Only Domain Adaptation in LLM-Based ASR 2026 · arXiv:2605.14340

[3] LLM-based ASR We follow an LLM-based ASR framework where the LLM is conditioned on an acoustic representation [1]

[4] Hours” denotes the total dura- tion of paired audio-text data used for source training, and “#Samples

[5] Unlike methods relying only on heuristic em- bedding manipulation, TE2SL employs a learnable Conformer- based refinement module

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Refining Pseudo-Audio Prompts with Speech-Text Alignment for Text-Only Domain Adaptation in LLM-Based ASR

Receipt and verification

First computed	2026-05-17T23:39:08.197109Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bf205ddb24ebeaca0badb350990dbe3e5753d48b5fdf7d4fe6de17a56c5f7109

Aliases

arxiv: 2605.14340 · arxiv_version: 2605.14340v1 · doi: 10.48550/arxiv.2605.14340 · pith_short_12: X4QF3WZE5PVM · pith_short_16: X4QF3WZE5PVMUC5N · pith_short_8: X4QF3WZE

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/X4QF3WZE5PVMUC5NWNIJSDN6HZ \
  | 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: bf205ddb24ebeaca0badb350990dbe3e5753d48b5fdf7d4fe6de17a56c5f7109

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "daaac886ae817f2ba908d326b725d6ec2c80a8b9e8562b77915aaa4bdf4d3fdd",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-05-14T04:04:03Z",
    "title_canon_sha256": "1c8689ae5da7930917c1650ac6b5e0279c774d0dcd5672e3fc45b26fe561eed2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14340",
    "kind": "arxiv",
    "version": 1
  }
}