Speech-centric machine learning systems have revolutionized many leading domains ranging from transportation and healthcare to education and defense, profoundly changing how people live, work, and interact with each other. However, recent studies have demonstrated that many speech-centric ML systems may need to be considered more trustworthy for broader deployment. Specifically, concerns over privacy breaches, discriminating performance, and vulnerability to adversarial attacks have all been discovered in ML research fields. In order to address the above challenges and risks, a significant number of efforts have been made to ensure these ML systems are trustworthy, especially private, safe, and fair. In this paper, we conduct the first comprehensive survey on speech-centric trustworthy ML topics related to privacy, safety, and fairness. In addition to serving as a summary report for the research community, we point out several promising future research directions to inspire the researchers who wish to explore further in this area.

翻译：以语音为中心的机器学习系统已彻底改变了从交通、医疗到教育和国防等多个主导领域，深刻影响着人们的生活、工作及相互交流方式。然而，近期研究表明，许多以语音为中心的机器学习系统在更广泛部署时可能需进一步考量其可靠性。具体而言，隐私泄露、性能歧视以及对对抗攻击的脆弱性等问题已在机器学习研究领域中被发现。为应对上述挑战与风险，大量研究致力于确保这些机器学习系统具备可靠性，尤其是隐私性、安全性和公平性。本文首次对以语音为中心的可靠机器学习中涉及隐私、安全与公平的主题进行了全面综述。除作为研究领域的总结报告外，本文还指出了若干有前景的未来研究方向，以激励希望在此领域深入探索的研究人员。