Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but also navigate the intricacies of linguistic diversity. In this paper, we address the aforementioned ASR challenge, focusing on the Tunisian dialect. First, textual and audio data is collected and in some cases annotated. Second, we explore self-supervision, semi-supervision and few-shot code-switching approaches to push the state-of-the-art on different Tunisian test sets; covering different acoustic, linguistic and prosodic conditions. Finally, and given the absence of conventional spelling, we produce a human evaluation of our transcripts to avoid the noise coming from spelling inadequacies in our testing references. Our models, allowing to transcribe audio samples in a linguistic mix involving Tunisian Arabic, English and French, and all the data used during training and testing are released for public use and further improvements.

翻译：构建有效的方言自动语音识别（ASR）方案需要创新方法，既需解决数据匮乏问题，又要应对语言多样性的复杂性。本文针对上述ASR挑战，聚焦突尼斯方言展开研究。首先，我们收集了文本与音频数据，并对部分数据进行了标注。其次，我们探索了自监督、半监督及少样本代码混合方法，以推动多个突尼斯测试集的最优性能，这些测试集涵盖不同的声学、语言和韵律条件。最后，鉴于缺乏标准拼写体系，我们对生成的转录文本进行了人工评估，以规避测试参考中拼写不规范带来的干扰。我们训练的模型能够转录包含突尼斯阿拉伯语、英语和法语的混合语言音频样本，所有训练与测试数据均已开源，供公众使用及后续改进。