Philip Anastassiou
Philip Anastassiou
Speech Synthesis Engineer at TikTok

Hello – my name is Philip and I am a musician and machine learning researcher living in San Francisco. I am interested in the combination of art and machine intelligence with the goal of developing new tools for creative expression.

I am a Speech Synthesis Engineer on the Speech, Audio, and Music Intelligence (SAMI) team at ByteDance/TikTok. I completed my M.S. in Computer Science and B.A. in Theatre at Columbia University.

My research interests include deep generative modeling, self-supervised representation and transfer learning, knowledge distillation, and digital signal processing. I am especially interested in neural end-to-end learning for speech, audio, music, and natural language processing tasks.

If you would like to connect, please feel free to reach me at philip [dot] anastassiou [at] pm [dot] me.

DOWNLOAD RESUME (PDF)