Reference Free Learning for Speech Enhancement and Speech Assessment 

Anurag Kumar is a research scientist and technical research lead at Meta Reality Labs Research. His primary research interests are in machine learning for audio and speech processing and audio-visual learning. 

Kumar’s talk will be centered on improving the perceptual quality and intelligibility of speech signals, which is critical for improving communications in real and virtual world whether someone has normal hearing or some form of hearing impairment. He will present an outline of some of his recent research on both methods to enhance degraded speech as well as methods for speech assessment, and he will go in depth on his recent works on unsupervised and self-supervised approaches for speech enhancement and how speech signals from the wild—for which target signals are not available—and might be used for enhancement. 

Kumar has been recipient of several awards and recognition including Best Paper Finalist at CVPR 2022 and NCC 2014, finalist in Qualcomm Innovation Fellowship 2017, winner of Samsung Innovation Awards 2012, and travel grants from IEEE SPS and EURASIP.

The Voices of XR speaker series is made possible by Kathy McMorran Murray and the National Science Foundation (NSF) Research Traineeship (NRT) program as part of the Interdisciplinary Graduate Training in the Science, Technology, and Applications of Augmented and Virtual Reality at the University of Rochester (#1922591).