Ke Chen

Ke Chen is a Research Scientist at Adobe Research. His research interests lies in audio processing, analysis, and music information retrieval. He works in the field of audio source separation, algorithmic music composition, and others. He received a PhD degree in computer science and a master degree in music at University of California San Diego (UCSD) advised by Prof. Shlomo Dubnov and Prof. Taylor Berg-Kirkpatrick.

Please visit his personal website to get more information.

AI & Machine Learning Audio

Publications

December 6, 2026 Neural Information Processing Systems (NeurIPS)

TAC: Timestamped Audio Captioning

Sonal Kumar, Prem Seetharaman, Ke Chen, Oriol Nieto, Jiaqi Su, Zhepei Wang, Rithesh Kumar, Dinesh Manocha, Nicholas J. Bryan, Zeyu Jin, Justin Salamon

May 8, 2025 International Conference on Machine Learning (ICML)

FLAM: Frame-Wise Language-Audio Modeling

Yusong Wu, Christos Tsirigotis, Ke Chen, Cheng-Zhi Anna Huang, Aaron Courville, Oriol Nieto, Prem Seetharaman, Justin Salamon

August 28, 2024 Interspeech 2024

Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation

Ke Chen, Jiaqi Su, Taylor Berg-Kirkpatrick, Shlomo Dubnov, Zeyu Jin

April 14, 2024 International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

MDX-GAN: Enhancing Perceptual Quality in Multi-Class Source Separation Via Adversarial Training

Ke Chen, Jiaqi Su, Zeyu Jin

News

The Story of Project Dub Dub Dub: From Adobe MAX Sneak to cutting-edge AI translation tool inside Adobe Firefly

First introduced as Project Dub Dub Dub at Adobe MAX 2023, this AI tech now powers the cutting-edge translation tool in Adobe Firefly. It translates videos while matching the speaker’s voice, tone, and cadence. Explore the tech behind the magic!

July 17, 2025