Zeyu Jin

Research Scientist

Creative Intelligence Lab, San Francisco

Zeyu is a research scientist at Adobe Research in San Francisco. His research interests are at speech and music synthesis, deep learning, and human-computer interaction.

He received a Ph.D. degree in computer science from Princeton University adviced by Adam Finkelstein and M.S in music technology in Carnegie Mellon University. Between 2015 and 2017, he interned at Adobe for three times and presented his primary research project – VoCo – at Adobe MAX Sneaks (link to video) in 2016.

My Publications

FFTNet: a Real-Time Speaker-Dependent Neural Vocoder

Jin, Z., Finkelstein, A., Mysore, G., Lu, J. (Apr. 15, 2018)
The 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP oral)

VoCo: text-based insertion and replacement in audio narration

Jin, Z., Mysore, G., DiVerdi, S., Lu, J., Finkelstein, A. (Jul. 31, 2017)
ACM Transactions on Graphics (TOG) 36, no. 4 (2017): 96.

CUTE: a Concatenative Method for Voice Conversion Using Exemplar-based Unit Selection

Jin, Z., Finkelstein, A., DiVerdi, S., Lu, J., Mysore, G. (Mar. 1, 2016)
The 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),