Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs

• URL: http://arxiv.org/abs/2605.12242v1
• Date: Tue, 12 May 2026 15:11:36 GMT
• Title: Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs
• Abstract summary: ASR transcripts often contain disfluencies, such as fillers, repetitions, and false starts.<n>Most existing approaches rely on classical models that focus on identifying disfluent tokens for removal.<n>We propose a multilingual correction pipeline where a sequence tagger first marks disfluent tokens, and these signals guide instruction fine-tuning of an LLM to rewrite transcripts into fluent text.
• Score: 32.94544776067079
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applications like chatbots and voice assistants. If left unaddressed, such disfluencies can significantly degrade the reliability of downstream systems. Most existing approaches rely on classical models that focus on identifying disfluent tokens for removal. While this strategy is effective to some extent, it often disrupts grammatical structure and semantic coherence, leading to incomplete or unnatural sentences. Recent literature explored the use of large language models (LLMs); however, these efforts have primarily focused on disfluency detection or data augmentation, rather than performing comprehensive correction. We propose a multilingual correction pipeline where a sequence tagger first marks disfluent tokens, and these signals guide instruction fine-tuning of an LLM to rewrite transcripts into fluent text. To further improve reliability, we add a contrastive learning objective that penalizes the reproduction of disfluent tokens, encouraging the model to preserve grammar and meaning while removing disfluent artifacts. Our experiments across three Indian languages, namely Hindi, Bengali, and Marathi show consistent improvements over strong baselines, including multilingual sequence-to-sequence models. These results highlight that detection-only strategies are insufficient. Combining token-level cues with instruction tuning and contrastive learning provides a practical and scalable solution for multilingual disfluency correction in speech-driven NLP systems. We make the codes publicly available at https://github.com/deepak-kumar-98/Mind-the-Pause.

Related papers

• Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing [8.921166277011347]
  We show that models already encode both styles; the challenge is controlled activation.<n>Using coverage-aware decoder task tokens trained on parallel verbatim/intended transcript pairs, we raise German disfluency F1 from 10% to 79% zero-shot.<n>Full English-only fine-tuning surpasses all baselines in verbatim accuracy, disfluency detection, and intended-mode quality across both languages.
  arXiv  Detail & Related papers  (2026-07-21T10:19:17Z)
• Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning [0.19116784879310025]
  Large language models (LLMs) sometimes exhibit language confusion when generating non-English text.<n>We propose a tuning-free paradigm for reducing language confusion.<n>Within this paradigm, we introduce two methods: Language-Aware Token Boosting (LATB), which applies targeted perturbations to tokens associated with the desired language, and Adaptive Language-Aware Token Boosting (Adaptive-LATB), which dynamically adjusts these perturbations based on the model's confidence in the intended language.
  arXiv  Detail & Related papers  (2026-06-08T03:47:07Z)
• Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation [3.6330067010404705]
  Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination.<n>Recent studies link this issue to language bias-the tendency of LVLMs to over-rely on text while neglecting visual inputs.<n>We provide a systematic study of language bias and identify its root in modality misalignment during training.
  arXiv  Detail & Related papers  (2026-05-24T12:23:13Z)
• Few-Shot Contrastive Adaptation for Audio Abuse Detection in Low-Resource Indic Languages [3.5238606794194816]
  Abusive speech detection is becoming increasingly important as social media shifts towards voice-based interaction.<n>We investigate whether Contrastive Language-Audio Pre-training can support abusive speech detection directly from audio.
  arXiv  Detail & Related papers  (2026-04-10T08:23:03Z)
• LiteToken: Removing Intermediate Merge Residues From BPE Tokenizers [76.59130257385826]
  Intermediate merge residues in BPE vocabularies are frequent during merge learning so that retained in the final vocabulary, but are mostly further merged and rarely emitted when tokenizing the corpus during tokenizer usage.<n>We present a systematic empirical characterization of this phenomenon across commonly used tokenizers and introduce LiteToken, a simple method for removing residue tokens.<n>Experiments show that LiteToken reduces token fragmentation, reduces parameters, and improves robustness to noisy or misspelled inputs, while preserving overall performance.
  arXiv  Detail & Related papers  (2026-02-04T16:19:05Z)
• Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation [50.93756215410832]
  This paper introduces the Language Confusion Gate (LCG), a lightweight, plug-in solution that filters tokens during decoding.<n>The LCG is trained using norm-adjusted self-distillation to predict appropriate language families and apply masking only when needed.
  arXiv  Detail & Related papers  (2025-10-20T14:02:37Z)
• Smooth Operators: LLMs Translating Imperfect Hints into Disfluency-Rich Transcripts [5.439020425819001]
  Large language models (LLMs) are versatile learners capable of processing both lexical and non-lexical inputs.<n>We propose a novel approach to disfluencies as explicit tokens with timestamps, enabling the generation of fully annotated disfluency-rich transcripts.
  arXiv  Detail & Related papers  (2025-06-23T11:04:20Z)
• Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation [79.96416609433724]
  Zero-shot translation (ZST) aims to translate between unseen language pairs in training data. The common practice to guide the zero-shot language mapping during inference is to deliberately insert the source and target language IDs. Recent studies have shown that language IDs sometimes fail to navigate the ZST task, making them suffer from the off-target problem.
  arXiv  Detail & Related papers  (2023-09-28T17:02:36Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Adversarial Training For Low-Resource Disfluency Correction [50.51901599433536]
  We propose an adversarially-trained sequence-tagging model for Disfluency Correction (DC) We show the benefit of our proposed technique, which crucially depends on synthetically generated disfluent data, by evaluating it for DC in three Indian languages. Our technique also performs well in removing stuttering disfluencies in ASR transcripts introduced by speech impairments.
  arXiv  Detail & Related papers  (2023-06-10T08:58:53Z)
• Keypoint based Sign Language Translation without Glosses [7.240731862549344]
  We propose a new keypoint normalization method for performing translation based on the skeleton point of the signer. It contributed to performance improvement by a customized normalization method depending on the body parts. Our method can be applied to various datasets in a way that can be applied to datasets without glosses.
  arXiv  Detail & Related papers  (2022-04-22T05:37:56Z)
• Zero-Shot Cross-lingual Aphasia Detection using Automatic Speech Recognition [3.2631198264090746]
  Aphasia is a common speech and language disorder, typically caused by a brain injury or a stroke, that affects millions of people worldwide. We propose an end-to-end pipeline using pre-trained Automatic Speech Recognition (ASR) models that share cross-lingual speech representations.
  arXiv  Detail & Related papers  (2022-04-01T14:05:02Z)
• Lexically Aware Semi-Supervised Learning for OCR Post-Correction [90.54336622024299]
  Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Previous work has demonstrated the utility of neural post-correction methods on recognition of less-well-resourced languages. We present a semi-supervised learning method that makes it possible to utilize raw images to improve performance.
  arXiv  Detail & Related papers  (2021-11-04T04:39:02Z)

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.