In this paper, we describe a spoken Arabic dialect identification (ADI) model
for Arabic that consistently outperforms previously published results on two
benchmark datasets: ADI-5 and ADI-17. We explore two architectural variations:
ResNet and ECAPA-TDNN, coupled with two types of acoustic features: MFCCs and
features exratected from the pre-trained self-supervised model UniSpeech-SAT
Large, as well as a fusion of all four variants. We find that individually,
ECAPA-TDNN network outperforms ResNet, and models with UniSpeech-SAT features
outperform models with MFCCs by a large margin. Furthermore, a fusion of all
four variants consistently outperforms individual models. Our best models
outperform previously reported results on both datasets, with accuracies of
84.7% and 96.9% on ADI-5 and ADI-17, respectively.

本篇论文描述了一个用于阿拉伯语的口语方言识别 (ADI) 模型，该模型在两个基准数据集 ADI-5 和 ADI-17 上始终表现优于先前发表的结果。我们探索了两种不同的架构变体：ResNet 和 ECAPA-TDNN，以及两种类型的声学特征：MFCC 和从预训练的自监督模型 UniSpeech-SAT Large 提取的特征，以及所有四个变体的融合。我们发现，ECAPA-TDNN 网络表现优于 ResNet，而具有 UniSpeech-SAT 特征的模型远远优于具有 MFCC 特征的模型。此外，所有四个变体的融合一致优于单个模型。我们的最佳模型在两个数据集上的准确率分别为 84.7% 和 96.9%，超过了先前报道的结果。