In this episode of IEEE Signal processing Society podcast, Dr. Shinji Watanabe, an Associate Professor at Carnegie Mellon University interviews two guests: Dr. Jonathan Le Roux, Distinguished Research Scientist and Dr. Gordon Wichern, both from Mitsubishi Electric Research Laboratories (MERL).
Dr. Jonathan Le Roux
Dr. Jonathan Le Roux is a Distinguished Research Scientist and Senior Team Leader at Mitsubishi Electric Research Laboratories (MERL) in Massachusetts. His research interests focus on signal processing and machine learning for speech and audio. He has authored more than 200 articles, along with 50 granted patents. He has been a member of prestigious academic societies such as IEEE Signal Processing Society’s Audio and Acoustic Signal Processing Technical Committee (AASP-TC), where he currently serves as the Vice Chair. He is also the Founder and Chair of the Speech and Audio in the Northeast (SANE) workshop series. Additionally, he served as a General Co-Chair of the 2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).
Dr. Gordon Wichern
Dr. Gordon Wichern is a Lead Research Scientist at Mitsubishi Electric Research Laboratories (MERL) in Massachusetts. His research mainly focusses on audio source separation and industrial anomaly detection. He was member of the Technical Staff at Massachusetts Institute of Technology (MIT) Lincoln Laboratory. He was also involved in a research team at iZotope, where he focused on applying novel signal processing and machine learning techniques to music and post-production software. Currently, he serves as the Chair of the AES Technical Committee on Machine Learning and Artificial Intelligence (TC-MLAI). He is also a member of the IEEE Audio and Acoustic Signal Processing Technical Committee (AASP-TC).
In this episode, Dr. Le Roux and Dr. Wichern discuss approaches for detecting unusual noise from machine, despite having background noise, and improving the performance of speech-separation systems under practical conditions. They also discuss about connecting open research with real-world problems and how these challenges could function as an effective space for training young researchers and interns. The conversation explore emerging challenges in the field, including growing complexity of learned metrics and computational demands.
