PulseAugur
EN
LIVE 08:23:43

New method boosts speech recognition for code-switching

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new contrastive training method to improve automatic speech recognition for code-switching, which involves alternating between languages within a single utterance. This approach identifies critical code-switching points and generates plausible "near-miss" hypotheses using large language models. Fine-tuning the Whisper-small model with this technique demonstrated over a 2% reduction in error rates on specific code-switching datasets. AI

IMPACT Enhances ASR robustness for multilingual users, potentially improving accessibility and usability of voice interfaces.

RANK_REASON The cluster contains an academic paper detailing a new method for improving speech recognition.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New method boosts speech recognition for code-switching

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Tung X. Nguyen, Hieu Minh Truong, Giang-Son Nguyen, Nhu Vo, Wray Buntine, Dung D. Le ·

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

    arXiv:2606.06985v1 Announce Type: new Abstract: 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 tra…

  2. arXiv cs.CL TIER_1 English(EN) · Dung D. Le ·

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

    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-…

RELATED ENTITIES

RELATED TOPICS