Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring
Ahmed Zahran, Aly A. Fahmy, Khaled Wassif, Hanaa Bayomi
Abstract
Automatic pronunciation assessment models are regularly used in language learning applications. Common methodologies for pronunciation assessment use feature-based approaches, such as the Goodness-of-Pronunciation (GOP) approach, or deep learning speech recognition models to perform speech assessment. With the rise of transformers, pre-trained self-supervised learning (SSL) models have been utilized to extract contextual speech representations, showing improvements in various downstream tasks. In this study, we propose the end-to-end regressor (E2E-R) model for pronunciation scoring. E2E-R is trained using a two-step training process. In the first step, the pre-trained SSL model is fine-tuned on a phoneme recognition task to obtain better representations for pronounced phonemes. In the second step, transfer learning is used to obtain a pronunciation scoring model that uses a Siamese neural network to compare the pronounced phoneme representations to embeddings of the canonical phonemes and produce the final pronunciation scores. E2E-R achieves a Pearson correlation coefficient (PCC) of 0.68, which is similar to the state-of-the-art GOPT-PAII model while eliminating the need for training on additional native speech data, feature engineering, or external forced alignment modules. To our knowledge, this work presents the first utilization of a pre-trained SSL model for end-to-end phoneme-level pronunciation scoring on raw speech waveforms.