In this work, we explore Parameter-Efficient-Learning (PEL) techniques to repurpose a General-Purpose-Speech (GSM) model for Arabic dialect identification (ADI). Specifically, we investigate different setups to incorporate trainable features into a multi-layer encoder-decoder GSM formulation under frozen pre-trained settings. Our architecture includes residual adapter and model reprogramming (input-prompting). We design a token-level label mapping to condition the GSM for Arabic Dialect Identification (ADI). This is challenging due to the high variation in vocabulary and pronunciation among the numerous regional dialects. We achieve new state-of-the-art accuracy on the ADI-17 dataset by vanilla fine-tuning. We further reduce the training budgets with the PEL method, which performs within 1.86% accuracy to fine-tuning using only 2.5% of (extra) network trainable parameters. Our study demonstrates how to identify Arabic dialects using a small dataset and limited computation with open source code and pre-trained models.

翻译：摘要：本文探索了参数高效学习（PEL）技术，以重新利用通用语音模型（GSM）进行阿拉伯方言识别（ADI）。具体而言，我们在冻结预训练设置下研究不同方案，将可训练特征融入多层编码器-解码器GSM架构。我们的架构包含残差适配器和模型重编程（输入提示）。我们设计了令牌级标签映射，使GSM能够适应阿拉伯方言识别（ADI）。由于众多区域方言在词汇和发音上存在高度变异性，这一任务具有挑战性。通过标准微调，我们在ADI-17数据集上实现了新的最先进准确率。我们进一步利用PEL方法降低了训练预算，该方法在仅使用额外网络参数2.5%的情况下，性能与微调相差1.86%的准确率。本研究展示了如何利用小型数据集和有限计算资源识别阿拉伯方言，并提供了开源代码和预训练模型。