Published:
Author: Dino Lencioni
Category:

Berrak Sisman joined Johns Hopkins this month as an assistant professor in the Whiting School of Engineering’s Department of Electrical and Computer Engineering and a member of the AI-X Bloomberg Distinguished Professorship Cluster. She leads the Speech & Machine Learning (SMILE) Lab,  advancing neural models for speech information processing.

Internationally recognized for her work in deep learning, speech synthesis, and the study of emotion in speech, Sisman earned her PhD from the National University of Singapore in 2020 and held research roles in the UK and Japan before joining Johns Hopkins from the University of Texas at Dallas.

1. What are your research interests and what specific problem are addressing?

My current research focuses on AI and speech processing, particularly in speech synthesis, voice conversion, and the study of emotion and expressiveness in speech. I am also exploring how speech synthesis can be applied in the medical domain, including innovative areas like brain-to-speech synthesis and assistive technologies for individuals with speaking disabilities. Another key focus is on developing secure speech technology, especially detecting synthetic voices, even when they are highly emotional and human-like. As speech synthesis technology becomes more advanced, distinguishing between human and synthetic voices becomes increasingly challenging, particularly when expressiveness is involved. I am excited to tackle these challenges with my team at Johns Hopkins.

2. What inspired you to pursue a career in electrical and computer engineering, and what excites you most about joining the Johns Hopkins community?

I have always been passionate about engineering and solving real-world problems. Electrical and computer engineering particularly appealed to me because it bridges hardware and software expertise, enabling work on a wide range of impactful applications. Joining Johns Hopkins University as a faculty member is an incredible opportunity to be part of a leading institution in AI and speech technology. I am especially thrilled to collaborate with talented students and colleagues here. Together, I believe we can significantly advance AI and develop secure speech technologies that truly benefit society.

3. What are the biggest challenges and opportunities in your field over the next decade?

The rapid growth of the field is exhilarating, as it opens numerous opportunities to create a positive societal impact. However, this growth also presents challenges, such as the risk of prioritizing speed or hype over rigorous scientific exploration. Striking a balance between innovation and maintaining scientific curiosity will be a crucial focus for the next decade.

4. Where did you grow up and where did you live before the Baltimore/DC area?

I have had the privilege of living in different parts of the world, which has given me a deep appreciation for diverse cultures. I grew up in Turkey and spent seven or eight years in Singapore, first pursuing my PhD and later as a researcher. Additionally, I have lived for shorter periods in Scotland and Japan as an exchange student. Before moving to the Baltimore/DC area, I spent two and a half years in Dallas, Texas.