Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning
Researchers have developed an automated system to evaluate the pronunciation of Korean toddlers, addressing a gap in current assessment tools. The system utilizes neural speaker diarization and self-supervised learning techniques to analyze speech recordings. Experiments on a newly created corpus of 53 children's recordings showed promising results, with an ensemble model achieving a mean balanced accuracy of 0.782 for pronunciation scoring. AI
IMPACT Provides a novel approach to speech analysis for early childhood development, potentially improving diagnostic accuracy for speech sound disorders.