Skip to content
AI News HubLIVE
Original source2 min read

Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems

Summary

This paper proposes a non-autoregressive weighted lookahead scoring method for punctuation restoration in streaming ASR, achieving 4-class macro F1 of 0.893 without fine-tuning and 0.937 after fine-tuning on IWSLT 2017, outperforming prompt-based and fine-tuned ELECTRA baselines.

SourcearXiv Computational LinguisticsAuthor: Sungmook Woo, Hyungu Kang, Chanwoo Kim
Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.05179] Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems

[Submitted on 18 Apr 2026]

Title:Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems

View a PDF of the paper titled Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems, by Sungmook Woo and 2 other authors

View PDF HTML (experimental)

Abstract:Punctuation restoration improves ASR (Automatic Speech Recognition) readability. However streaming ASR requires online decisions with limited future context. In streaming ASR, the system predicts punctuation incrementally, which makes generation-based approaches prone to latency and alignment failures under boundary-wise evaluation. This paper proposes a non-autoregressive scoring method (no free-form generation) that preserves the input transcript and makes a decision at each word boundary. Our method compares punctuation insertion hypotheses against a no-insertion baseline under a bounded K-subword-token lookahead, and calibrates decisions using a weight {\alpha} and a validation-calibrated threshold {\tau} (no parameter updates during inference). On IWSLT 2017, our scoring method achieves a 4-class macro F1 of 0.893 in the no fine-tuning setting (validation-calibrated, K=2) and 0.937 after fine-tuning (K=2), outperforming the prompt-based baseline (0.566) and a fine-tuned ELECTRA baseline (0.913) under the same lookahead budget. We analyze the impact of the lookahead budget through ablation studies on K.

Comments: Accepted for presentation at The International Joint Conference on Neural Networks (IJCNN) 2026

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2606.05179 [cs.CL]

(or arXiv:2606.05179v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.05179

arXiv-issued DOI via DataCite

Submission history

From: Chanwoo Kim [view email] [v1] Sat, 18 Apr 2026 01:03:33 UTC (275 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems, by Sungmook Woo and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Proposes a non-autoregressive scoring method that avoids latency and alignment failures of generation-based approaches in streaming settings
  • Compares punctuation insertion hypotheses against a no-insertion baseline under bounded K-subword lookahead, calibrating decisions with weight α and validation-calibrated threshold τ
  • Achieves 0.893 macro F1 without fine-tuning and 0.937 after fine-tuning on IWSLT 2017, surpassing prompt-based baseline (0.566) and fine-tuned ELECTRA (0.913)
  • Analyzes the impact of lookahead budget K through ablation studies

Highlights and analysis are generated automatically and may contain errors. Check the original source.