Accent classification or AC is a task to predict the accent type of an input utterance, and it can be used as a preliminary step toward accented speech recognition and accent conversion. Existing studies have often achieved such classification by training a neural network model to minimize the classification error of the predicted accent label, which can be obtained as a model output. Since we optimize the entire model only from the perspective of classification loss during training time in this approach, the model might learn to predict the accent type from irrelevant features, such as individual speaker identity, which are not informative during test time. To address this problem, we propose a GE2E-AC, in which we train a model to extract accent embedding or AE of an input utterance such that the AEs of the same accent class get closer, instead of directly minimizing the classification loss. We experimentally show the effectiveness of the proposed GE2E-AC, compared to the baseline model trained with the conventional cross-entropy-based loss.

翻译：口音分类（Accent Classification，AC）是一项预测输入语音片段所属口音类型的任务，可作为口音语音识别与口音转换的预处理步骤。现有研究通常通过训练神经网络模型以最小化预测口音标签的分类误差来实现此类分类，该标签可直接作为模型输出获得。由于在此方法中，我们仅在训练阶段从分类损失的角度优化整个模型，模型可能从无关特征（如个体说话人身份）中学习预测口音类型，而这些特征在测试阶段并不具有信息性。为解决此问题，我们提出GE2E-AC方法，该方法训练模型提取输入语音片段的口音嵌入向量，使得相同口音类别的嵌入向量彼此靠近，而非直接最小化分类损失。通过实验，我们证明了所提出的GE2E-AC相较于使用传统基于交叉熵损失的基线模型具有更优性能。