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

• URL: http://arxiv.org/abs/2606.05179v1
• Date: Sat, 18 Apr 2026 01:03:33 GMT
• Title: Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems
• Abstract summary: Punctuation restoration improves ASR (Automatic Speech Recognition) readability.<n>Streaming ASR requires online decisions with limited future context.<n>This paper proposes a non-autoregressive scoring method that preserves the input transcript and makes a decision at each word boundary.
• Score: 4.703098868120046
• License: http://creativecommons.org/licenses/by/4.0/
• 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 α and a validation-calibrated threshold τ (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.

Related papers

• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• From Text to Parameters: Predicting Item Parameters from Embedding Regularization with Reliability and Design Ceilings [1.8194320623567561]
  We propose an evaluation framework combining regularized regression on item text embeddings.<n>We find that item difficulty is highly predictable from text.<n>We show that embedding based regression matches leaderboard RMSE despite explaining almost no variance.
  arXiv  Detail & Related papers  (2026-07-08T08:34:46Z)
• Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation [53.844308305341166]
  We propose textbfAgentic ASR, a closed-loop framework that combines a single-pass ASR front-end with semantic correction, intent routing, and reasoning-based editing.<n> Experiments on multilingual, named-entity-intensive, and code-switching benchmarks show that iterative interaction consistently reduces semantic errors.
  arXiv  Detail & Related papers  (2026-05-28T06:23:31Z)
• Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions [2.5565719921628443]
  Federated learning systems must support data deletion requests to comply with privacy regulations.<n>We present HF-KCU, a method that removes a client's contribution by approximating the influence through conjugate iterations in Krylov subspaces.<n>We provide convergence guarantees showing that the Krylov approximation error decreases as O((k 1/2-1)/(k1/2+1) where k is the Hessian condition number.
  arXiv  Detail & Related papers  (2026-05-19T18:00:39Z)
• OCRR: A Benchmark for Online Correction Recovery under Distribution Shift [0.0]
  OCRR (Online Correction Recovery Rate) is a benchmark that streams a corpus through a classification system and applies oracle or corrections to wrong predictions.<n>It beats the next-best published continual-learning baseline by 32.6 percentage points at equal memory budget.<n>It also beats LoRA-on-DeBERTa-v3-large by 84.6 percentage points on retention.
  arXiv  Detail & Related papers  (2026-05-04T20:51:07Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization [6.908972852063454]
  Temporal action localization requires both precise boundary detection and computational efficiency.<n>We address this through two complementary innovations: Boundary Distance Regression (BDR) and Adaptive Temporal Refinement (ATR)<n>On THUMOS14, our method achieves 56.5% mAP@0.7 with 151G FLOPs, using 36% fewer FLOPs than ActionFormer++ (55.7% mAP@0.7 at 235G)
  arXiv  Detail & Related papers  (2025-11-06T00:41:54Z)
• Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals [6.5422130090856925]
  Self-Truncation Best-of-N (ST-BoN) mitigates this by truncating unpromising paths early.<n>We present KL-Adjusted Pruned Path Algorithm (KAPPA), an inference-time method that combines Kullback-Leibler divergence, confidence, and entropy into a principled scoring function.
  arXiv  Detail & Related papers  (2025-11-01T20:41:22Z)
• Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices [8.77712061194924]
  We present a finite-state transducer (FST) technique for rewriting wordpiece lattices generated by Transformer-based CTC models. Our algorithm performs grapheme-to-phoneme (G2P) conversion directly from wordpieces into phonemes, avoiding explicit word representations. We achieved up to a 15.2% relative reduction in sentence error rate (SER) on a test set with contextually relevant entities.
  arXiv  Detail & Related papers  (2024-09-24T21:42:25Z)
• Sequence Transduction with Graph-based Supervision [96.04967815520193]
  We present a new transducer objective function that generalizes the RNN-T loss to accept a graph representation of the labels. We demonstrate that transducer-based ASR with CTC-like lattice achieves better results compared to standard RNN-T.
  arXiv  Detail & Related papers  (2021-11-01T21:51:42Z)
• FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition [90.34177266618143]
  We propose FastCorrect, a novel NAR error correction model based on edit alignment. FastCorrect speeds up the inference by 6-9 times and maintains the accuracy (8-14% WER reduction) compared with the autoregressive correction model. It outperforms the accuracy of popular NAR models adopted in neural machine translation by a large margin.
  arXiv  Detail & Related papers  (2021-05-09T05:35:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.