Tingle Li

I am a first-year Ph.D. student at Berkeley Artificial Intelligence Research (BAIR) Lab, advised by Prof. Gopala Anumanchipalli.

Previously, I had the privilege to work with Prof. Hang Zhao from IIIS, Tsinghua University, Prof. Andrew Owens from The University of Michigan, and Prof. Ming Li from Duke University.

My research revolves around the intersections of audio signal processing and computer vision. I am particularly excited about studying training vision with audio texture and vice versa.

We learn from unlabeled data to manipulate the style of an image using sound.

High-quality speech recovery system for millimeter-wave radar without deafness.

With multi-modal data as inputs, the encoders from naive fusion training will suffer from learning insufficient representations of each modality.

Automatic video dubbing driven by a neural network.

One-way GAN training for non-parallel voice conversion.

The scope of attention is narrowed down to the intra-chunk musical features that are most likely to affect each other.

SoTA performance for speech activity detection and speaker identification.

Adapted Transformer to the speech separation for more efficient and generalizable performance.

A new mapping loss based on Hungarian algorithm that reduces time complexity while maintaining performance for speaker diarization.

Last updated Oct. 2022.
Template from Jon Barron.