paper-with-me

Papers

Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition

2026-06-05 · Tung X. Nguyen, Hieu Minh Truong, Giang Son Nguyen, Nhu Vo, Wray Buntine, Dung D. Le arxiv

Code-switching (CS), the alternation between multiple languages within a single utterance, remains challenging for Automatic Speech Recognition (ASR). To address this issue, we propose a Point-of-Interest (POI)-aware contrastive training framework that improves recognition at CS-critical regions. We first identify CS spans by adopting POI detection method from literature, then construct acoustically plausible near-miss hypotheses by perturbing POIs in ASR N-best outputs and expanding candidates with a large language model. Hard but plausible negatives are retained through filtering with acoustic, phonemic, and textual constraints. Finally, we fine-tune Whisper-small with LoRA using a POI-weighted cross-entropy anchor objective together with a multi-negative contrastive ranking loss. Experiments on CS-FLEURS (cmn-eng) and ViMedCSS (vie-eng) show consistent reductions of over 2% in both general and CS-aware error rates compared to standard LoRA fine-tuning.

📄 PDF Abstract BibTeX arXiv:2606.06985

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning

2021-01-31 · Mohamed R. Ibrahim, James Haworth, Nicola Christie, Tao Cheng

Cycling is a promising sustainable mode for commuting and leisure in cities, however, the fear of getting hit or fall reduces its wide expansion as a commuting mode. In this paper, we introduce a novel method called Cycl…

GPU

Explaining with Attribute-based and Relational Near Misses: An Interpretable Approach to Distinguishing Facial Expressions of Pain and Disgust

2023-08-27 · Bettina Finzel, Simon P. Kuhn, David E. Tafler, Ute Schmid

Explaining concepts by contrasting examples is an efficient and convenient way of giving insights into the reasons behind a classification decision. This is of particular interest in decision-critical domains, such as me…

AttributeExplanation Generation

Explainable AI Approach using Near Misses Analysis

2024-11-25 · Eran Kaufman, Avivit Levy

This paper introduces a novel XAI approach based on near-misses analysis (NMA). This approach reveals a hierarchy of logical 'concepts' inferred from the latent decision-making process of a Neural Network (NN) without de…

Decision Making

Training for Compositional Sensitivity Reduces Dense Retrieval Generalization

2026-03-16 · Radoslav Ralev, Aditeya Baral, Iliya Zhechev, Jen Agarwal 외 arxiv

Dense retrieval compresses texts into single embeddings ranked by cosine similarity. While efficient for recall, this interface is brittle for identity-level matching: minimal compositional edits (negation, role swaps) f…

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

2025-12-22 · Yongxin Wang, Zhicheng Yang, Meng Cao, Mingfei Han 외 arxiv

Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the u…

Reinforcement LearningMultimodal Reasoning