Jiaqi Su

Audio Research Scientist

San Francisco

Jiaqi Su is an audio research scientist at Adobe Research in San Francisco. Her research interests center on deep learning in audio, with focus on audio and speech processing problems such as speech enhancement, bandwidth extension, acoustic matching and speech source separation. She received her Ph.D. degree in computer science from Princeton University advised by Prof. Adam Finkelstein. Before that, she received her B.S. degree in computer science from Cornell University. Her work during internship was presented at 2019 Adobe Max Sneaks in name of “Project Awesome Audio”.

Publications

Controllable Speech Representation Learning Via Voice Conversion and AIC Loss

Wang, Y., Su, J., Finkelstein, A., Jin, Z. (May. 22, 2022)

ICASSP 2022

HiFi-GAN-2: Studio-quality speech enhancement via generative adversarial networks conditioned on acoustic features

Su, J., Jin, Z., Finkelstein, A. (Oct. 17, 2021)

IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)

Bandwidth Extension is All You Need

Su, J., Wang, Y., Finkelstein, A., Jin, Z. (Jun. 9, 2021)

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

HiFi-GAN: High-fidelity denoising and dereverberation based on speech deep features in adversarial networks