Kan Jen Cheng

I'm a student at UC Berkeley. Currently, I am doing audio research in Berkeley Speech Group.

My research interests center on auditory perception, sound synthesis, texture editing, and computer vision. Recognizing that human perception of the environment relies heavily on the interplay between auditory and visual cues, I aim to develop sophisticated multi-modal systems capable of integrating audio-visual information to enhance human understanding, interpretation, and interaction with the world.

Email  /  CV  /  Github

Research

I'm interested in deep learning, generative AI, and audio processing. Most of my research is about inferring the physical world (speech, sound etc) from audio. Some papers are highlighted.

A holistic benchmark for assessing emotional coherence in spoken dialogue systems through continuous, categorical, and perceptual metrics.

An exemplar-based analogy model for audio texture manipulation that uses paired speech examples to learn transformations.

Last updated:

Template from Jon Barron.