扭曲、驼峰与卵石：多语言语音识别模型呈现性别性能差距
Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps
AI总结：
本文系统评估两个多语言ASR模型在19种语言上的性别性能差距，发现差距无法由声学或词汇属性解释，但与模型内部性别可区分性相关，并强调训练数据可及性和细致评估对缓解性别差距的重要性。
摘要：
当前的自动语音识别（ASR）模型被设计为无需大幅改动即可跨多种语言和任务使用。然而，这种广泛的语言覆盖掩盖了语言内部的性能差距，例如不同性别之间的差距。我们的研究系统评估了两个广泛使用的多语言ASR模型在三个数据集上的表现，涵盖来自八个语系的19种语言和两种说话条件。我们的发现揭示了明显的性别差异，且优势群体因语言和模型而异。令人惊讶的是，这些差距无法用声学或词汇属性来解释。然而，探查模型内部状态揭示了其与性别性能差距的相关性。也就是说，使用探针在一种语言中区分说话者性别越容易，差距就越缩小，且更有利于女性说话者。我们的结果表明，即使在最先进的模型中，性别差异依然存在。我们的发现对多语言ASR系统的改进具有启示意义，强调了获取训练数据的机会以及进行细致评估以预测和缓解性别差距的重要性。我们在 https://github.com/g8a9/multilingual-asr-gender-gap 发布所有代码和工件。
英文摘要：
Current automatic speech recognition (ASR) models are designed to be used across many languages and tasks without substantial changes. However, this broad language coverage hides performance gaps within languages, for example, across genders. Our study systematically evaluates the performance of two widely used multilingual ASR models on three datasets, encompassing 19 languages from eight language families and two speaking conditions. Our findings reveal clear gender disparities, with the advantaged group varying across languages and models. Surprisingly, those gaps are not explained by acoustic or lexical properties. However, probing internal model states reveals a correlation with gendered performance gap. That is, the easier it is to distinguish speaker gender in a language using probes, the more the gap reduces, favoring female speakers. Our results show that gender disparities persist even in state-of-the-art models. Our findings have implications for the improvement of multilingual ASR systems, underscoring the importance of accessibility to training data and nuanced evaluation to predict and mitigate gender gaps. We release all code and artifacts at https://github.com/g8a9/multilingual-asr-gender-gap.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
