About me

Hello! I’m Soumi Maiti, a postdoctoral researcher at Carnegie Mellon University’s Language Technologies Institute. I work at WAVLab and advised by Shinji Watanabe. I’m passionate about various aspects of speech and language processing, which includes speech processing, speech synthesis, speech enhancement, speech evaluation, and machine learning in general. During my doctoral studies, I primarily focused on high-quality speech enhancement using speech synthesis techniques. Currently, I am working towards speech generation using advanced language models and multilingual speech processing.

My background and history

I earned my Ph.D. from the Graduate Center, City University of New York (CUNY), where I worked in the Speech Lab, advised by Micheal I. Mandel. My dissertation work was on speech enhancement using synthesis techniques. I earned B.Tech. in Computer Science from the Indian Institute of Engineering Science and Technology, Shibpur. I have worked as a machine learning engineer at Apple within the Text-To-Speech team. I career journey also includes research experience as a graduate student researcher / internships at Google and Interactions LLC. I contributed as an adjunct lecturer at Brooklyn College, CUNY, for three years and served as a Math Fellow at Hunter College.