Juan-Pablo Caceres

Juan-Pablo is a senior research engineer in the Creative Intelligence Lab of Adobe Research in San Francisco. Juan-Pablo’s research interests include signal processing and machine learning for audio and music applications.

Juan-Pablo completed his Ph.D. and M.A. from the Center for Computer Research in Music and Acoustics (CCRMA) at Stanford University. He enjoys transforming cutting-edge audio research into product-ready software.

AI & Machine Learning Audio

Publications

May 4, 2026 International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Stemphonic: All-at-once Flexible Multistem Music Generation

Shih-Lun Wu, Ge Zhu, Juan-Pablo Caceres, Cheng-Zhi Anna Huang, Nicholas J. Bryan

July 23, 2024 IEEE Signal Processing Letters, vol. 31, pp. 2365-2369

MusicHiFi: Fast High-Fidelity Stereo Vocoding

Ge Zhu, Juan-Pablo Caceres, Zhiyao Duan, Nicholas J. Bryan

June 4, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Transcription Free Filler Word Detection with Neural Semi-CRFs

Ge Zhu, Yujia Yan, Juan-Pablo Caceres, Zhiyao Duan

September 18, 2022 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022)

Filler Word Detection and Classification: A Dataset and Benchmark

Ge Zhu, Juan-Pablo Caceres, Justin Salamon

October 5, 2021 Arxiv

Neural Pitch-Shifting and Time-Stretching with Controllable LPCNet

Max Morrison, Zeyu Jin, Nicholas J. Bryan, Juan-Pablo Caceres, Bryan Pardo

June 6, 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Context-Aware Prosody Correction for Text-Based Speech Editing

Max Morrison, Lucas Rencker, Zeyu Jin, Nicholas J. Bryan, Juan-Pablo Caceres, Bryan Pardo

News

Researcher Spotlight: Juan-Pablo Caceres on the Love of Audio

Senior Research Engineer Juan-Pablo Caceres creates technologies that transform how people use and edit audio. Now, along with the Audio Research Group at Adobe Research, he is working to bring AI innovations to the creation of voice content.

December 7, 2020