Our voice encodes a uniquely identifiable pattern which can be used to infer private attributes, such as gender or identity, that an individual might wish not to reveal when using a speech recognition service. To prevent attribute inference attacks alongside speech recognition tasks, we present a generative adversarial network, GenGAN, that synthesises voices that conceal the gender or identity of a speaker. The proposed network includes a generator with a U-Net architecture that learns to fool a discriminator. We condition the generator only on gender information and use an adversarial loss between signal distortion and privacy preservation. We show that GenGAN improves the trade-off between privacy and utility compared to privacy-preserving representation learning methods that consider gender information as a sensitive attribute to protect.

翻译：我们的语音编码了一种独特的、可识别的模式,可以用来推断个人在使用语音识别服务时可能不愿透露的性别或身份等私人属性。为了防止将攻击与语音识别任务联系起来,我们提出了一个基因对抗网络,即GenGAN, 将隐藏发言者性别或身份的声音合成起来。提议的网络包括一个带有U-Net结构的生成器,该结构学会愚弄歧视者。我们仅将性别信息作为生成器的条件,使用信号扭曲与隐私保护之间的对抗性损失。我们表明GenGAN改进了隐私和效用之间的权衡,而不是将性别信息视为保护的敏感属性的隐私保护代表性学习方法。