未被听见的替代选择：面向语音转文本模型的对比解释
The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
AI总结：
本文提出一种新方法，通过分析输入频谱如何影响语音转文本模型在替代输出间的抉择，实现对比解释，用于性别识别任务中音频特征的准确识别。
摘要：
对比解释，即说明人工智能系统为何选择一个输出（目标）而非另一个（对照），在可解释人工智能中被认为比标准解释更具信息量和可解释性。然而，获得语音转文本（S2T）生成模型的此类解释仍是一个开放性挑战。受特征归因技术启发，我们提出了一种首次在S2T中获取对比解释的方法，通过分析输入频谱中各部分如何影响替代输出的选择。通过语音翻译中性别识别的案例研究，我们展示了该方法能够准确识别驱动选择某一性别而非另一性的音频特征。通过将对比解释的范围扩展到S2T，我们的工作为更好地理解S2T模型提供了基础。
英文摘要：
Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely regarded in explainable AI as more informative and interpretable than standard explanations. However, obtaining such explanations for speech-to-text (S2T) generative models remains an open challenge. Drawing from feature attribution techniques, we propose the first method to obtain contrastive explanations in S2T by analyzing how parts of the input spectrogram influence the choice between alternative outputs. Through a case study on gender assignment in speech translation, we show that our method accurately identifies the audio features that drive the selection of one gender over another. By extending the scope of contrastive explanations to S2T, our work provides a foundation for better understanding S2T models.
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。
