Pith Number

pith:OQWRAWNE

pith:2026:OQWRAWNEV3JYCTH5XTJR3KVMZ2

not attested not anchored not stored refs pending

Contextual Biasing for Streaming ASR via CTC-based Word Spotting

Berlin Chen, Kai-Chen Tsai, Tien-Hong Lo, Yun-Ting Sun

A streaming extension of CTC-based word spotting enables real-time contextual biasing in ASR by tracking keyword paths across chunks and committing only to stable segments.

arxiv:2605.18222 v1 · 2026-05-18 · eess.AS

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{OQWRAWNEV3JYCTH5XTJR3KVMZ2}

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

Experimental results show that our method reduces overall WER and effectively improves keyword F-score, demonstrating its effectiveness for real-time ASR applications.

C2weakest assumption

The incremental commitment mechanism successfully identifies segments guaranteed not to be affected by future audio while deferring uncertain regions, enabling both low latency and stable output without harming overall accuracy.

C3one line summary

Introduces a streaming CTC-WS method with stateful token passing and incremental commitment for low-latency contextual biasing in ASR, claiming reduced WER and improved keyword F-score.

References

18 extracted · 0 resolved · 0 Pith anchors

[1] A Survey on Deep Learning for Named Entity Recognition, 2022

[2] Deep Context: End-to-End Contextual Speech Recognition, 2018

[3] Contextual RNN-T for Open Domain ASR, 2020

[4] PromptASR for Contextualized ASR with Controllable Style, 2024

[5] Contextualized Streaming End-to-End Speech Recognition with Trie- Based Deep Biasing and Shallow Fusion, 2021

Receipt and verification

First computed	2026-05-20T00:05:51.150826Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

742d1059a4aed3814cfdbcd31daaaccebd9aa71fa82769506ee6a5c34789be71

Aliases

arxiv: 2605.18222 · arxiv_version: 2605.18222v1 · doi: 10.48550/arxiv.2605.18222 · pith_short_12: OQWRAWNEV3JY · pith_short_16: OQWRAWNEV3JYCTH5 · pith_short_8: OQWRAWNE

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/OQWRAWNEV3JYCTH5XTJR3KVMZ2 \
  | 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: 742d1059a4aed3814cfdbcd31daaaccebd9aa71fa82769506ee6a5c34789be71

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "208efa60de962a0ea7e350b8682dac41b6c1ce2304b0736ea2c26945c0e4fde7",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "eess.AS",
    "submitted_at": "2026-05-18T11:06:44Z",
    "title_canon_sha256": "3f8df42c862067ab610b02bc55b5068d868d9b241e92c1a041f52a14bd4694ee"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.18222",
    "kind": "arxiv",
    "version": 1
  }
}