Jonathan Le Roux Email & Phone Number

At MERL, the core of my work is on machine learning applied to audio signal processing, particularly speech enhancement and source separation. I also actively participate in other projects in the Speech and Audio team, involving all parts of the speech processing pipeline, such as acoustic modeling, language modeling, topic modeling, natural language undersanding, dialog systems, and user prediction.Prior to joining MERL, my Ph.D. and post-doc work included F0 estimation for single/multiple speakers and in noisy environments, spectrogram-consistency-aware signal processing, fast signal reconstruction from magnitude spectrograms, model-based source separation methods using harmonically-constrained GMMs as well as various extensions to non-negative matrix factorization (NMF).Specialties: Audio signal processing, Deep learning, Machine listening, Model-based approaches, Source separation, Machine learning, Statistical inference, Latent variable models

Listed skills include Machine Learning, Signal Processing, Pattern Recognition, Audio Processing, and 3 others.