Scholar

Christian J. Steinmetz

Google Scholar ID: jSvSfIMAAAAJ

Queen Mary University of London

deep learningaudioaudio signal processing

Citations & Impact

All-time

Citations

903

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Published in PMLR, NeurIPS, ICASSP, WASPAA (Best Paper x2), DAFx, and JAES, and won awards for audio plugins at IEEE and AES; submitted a number of patents related to deep learning systems for audio processing.

Research Experience

Suno: Research Scientist (April 2024 - Present); Tape It: Research Scientist (January 2022 - January 2024); Adobe Research: Research Scientist Intern (June 2022 - September 2022, June 2021 - September 2021); Meta | Reality Labs: Research Scientist Intern (June 2020 - November 2020); Dolby Laboratories: Research Intern (January 2020 - June 2020); Bose Corporation: Research Intern (Summer 2019); Clemson University: Audio Assistant (Fall 2017 - Spring 2019); Cirrus Logic, Inc.: Mixed Signal Audio Applications Engineer Intern (Summer 2017 & Summer 2018); WSBF-FM Clemson Radio Station: Chief Engineer (Fall 2016 - Spring 2019), Equipment Engineer (Fall 2016 - Spring 2019), Producer & Live Sound Engineer (Fall 2015 - Fall 2018); Vertronix Research Corporation: Electrical Engineering Intern (Summer 2014, 2015, & 2016).

Education

Queen Mary University of London: PhD in Artificial Intelligence and Music (Advisors: Joshua D. Reiss and Shanxin Yuan); Universitat Pompeu Fabra: Master in Sound and Music Computing (Advisor: Joan Serrà); Clemson University: B.S. in Electrical Engineering and B.A. in Production Studies in Performing Arts with a Concentration in Audio Technology, Minor in Mathematical Sciences (Advisor: Carl Baum).

Background

Research interests include applications of generative AI and machine learning in audio, with a PhD focus on audio enhancement and automatic control of DSP. Tasks covered include neural audio effects, audio synthesis, style transfer, room acoustics, self-supervised audio representations, automatic mixing and mastering, speech enhancement, source separation, beat tracking, and neural audio fingerprinting.

Miscellany