L-2-ARCTIC

The L-2-ARCTIC dataset is used to evaluate mispronunciation detection and diagnosis methods in language learning and speech therapy.

Papers using L-2-ARCTIC (9)

CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations2026Contrastive Regularization for Accent-Robust ASR2026Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach2025Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition2025Zero-Shot Text-to-Speech as Golden Speech Generator: A Systematic Framework and its Applicability in Automatic Pronunciation Assessment2024Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning2021 · 3 citesMispronunciation detection using self-supervised speech representations2023L1-aware Multilingual Mispronunciation Detection Framework2023Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis2024