Yunyun Wang is a researcher in the Speech AI Group. She earned her Ph.D. in Computer Science from Princeton University, where she worked with Professor Adam Finkelstein and Adobe researcher Zeyu Jin. Before joining as full-time, she interned with Adobe for three years, playing a key role in advancing generative speech technologies. She spearheaded Project GUMS (Generative Universal Model for Speech), which laid the foundation for subsequent innovations such as Project DubDubDub – an automatic voice translation system – and Voice Costume, a tool that enables users to transform their voices into virtual characters. Her current research centers on generative models for speech and audio content authentication.