Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar performance compared to traditional methods. However, SSL-based ASA systems are faced with at least three data-related challenges: limited annotated data, uneven distribution of learner proficiency levels and non-uniform score intervals between different CEFR proficiency levels. To address these challenges, we explore the use of two novel modeling strategies: metric-based classification and loss reweighting, leveraging distinct SSL-based embedding features. Extensive experimental results on the ICNALE benchmark dataset suggest that our approach can outperform existing strong baselines by a sizable margin, achieving a significant improvement of more than 10% in CEFR prediction accuracy.

翻译：自动化口语评估（ASA）通常涉及自动语音识别（ASR）以及从学习者语音的ASR转录文本中手工提取特征。最近，与传统的基于自监督学习（SSL）相比，自监督学习（SSL）已展现出卓越的性能。然而，基于SSL的ASA系统至少面临三个与数据相关的挑战：标注数据有限、学习者能力水平分布不均、以及不同CEFR能力水平之间的评分间隔不统一。为应对这些挑战，我们探索了两种新颖的建模策略：基于度量的分类和损失重加权，并利用了不同的SSL嵌入特征。在ICNALE基准数据集上的大量实验结果表明，我们的方法能够以显著优势超越现有强基线模型，在CEFR预测准确率上实现了超过10%的显著提升。