Zhepei Wang
Portrait of Zhepei Wang

Zhepei Wang

Researcher, Adobe Research

zhepeiw03 [at] gmail [dot] com

zhepeiw [at] ieee [dot] org

CV

Hello! I am a researcher at the MusicAI Group of Adobe Research. My work focuses on machine learning for music, audio, and speech, including music and audio understanding, text-to-music generation, sound recognition, source separation, speech enhancement, and multimodal representation learning.

Before joining Adobe, I was an applied scientist at Amazon Web Services (AWS) and also interned there several times, working on real-time speech enhancement, personalized audio processing, and enterprise search. I earned my Ph.D. in Computer Science from the University of Illinois Urbana-Champaign in 2023, advised by Prof. Paris Smaragdis. Prior to my Ph.D., I received my B.S. in Computer Science from Harvey Mudd College in 2018.

Selected Work

Representative figure for Rethinking Music Captioning with Music Metadata LLMs

In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) · 2026

Rethinking Music Captioning with Music Metadata LLMs

Irmak Bukey, Zhepei Wang, Chris Donahue, Nicholas J. Bryan

Paper
Representative figure for A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement

In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) · 2023

A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement

Zhepei Wang, Ritwik Giri, Devansh Shah, Jean-Marc Valin, Michael M. Goodwin, Paris Smaragdis

Paper Video Poster
Representative figure for Learning Representations for New Sound Classes With Continual Self-Supervised Learning

In IEEE Signal Processing Letters · 2022

Learning Representations for New Sound Classes With Continual Self-Supervised Learning

Zhepei Wang, Yusuf Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis

Paper Poster Code
Representative figure for Sudo RM -RF: Efficient Networks for Universal Audio Source Separation

In IEEE International Workshop on Machine Learning for Signal Processing (MLSP) · 2020

Sudo RM -RF: Efficient Networks for Universal Audio Source Separation

Efthymios Tzinis, Zhepei Wang, Paris Smaragdis

Paper Code
Representative figure for Continual Learning of New Sound Classes Using Generative Replay

In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · 2019

Continual Learning of New Sound Classes Using Generative Replay

Zhepei Wang, Yusuf Cem Subakan, Efthymios Tzinis, Paris Smaragdis, Laurent Charlin

Paper

Updates

May 2024

I have joined Adobe as a Research Scientist/Engineer under MusicAI Group.

Sep 2023

I have started my role as an applied scientist at AWS ChimeSDK Audio Science team.