BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Learning for Multifarious Speech Processing: Tackling Multipl
 e Speakers\, Microphones\, and Languages - Jonathan Le Roux\, Mitsubishi E
 lectric Research Labs\, USA
DTSTART:20190510T140000Z
DTEND:20190510T150000Z
UID:TALK124543@talks.cam.ac.uk
CONTACT:Prof. Ramji Venkataramanan
DESCRIPTION:Speech processing has been at the forefront of the recent deep
  learning revolution\, with major breakthroughs in automatic speech recogn
 ition\, speech enhancement\, and source separation. I will give an overvie
 w of deep learning techniques developed at MERL towards the goal of cracki
 ng the Tower of Babel version of the cocktail party problem\, that is\, se
 parating and/or recognizing the speech of multiple unknown speakers speaki
 ng simultaneously in multiple languages. I will also attempt to present li
 ve demonstrations with audience participation (weather\, time\, and networ
 k conditions permitting).\n \n*Bio*:\nJonathan Le Roux is a Senior Princip
 al Research Scientist and the Speech and Audio Team Leader at Mitsubishi E
 lectric Research Laboratories (MERL) in Cambridge\, Massachusetts. He comp
 leted his B.Sc. and M.Sc. degrees in Mathematics at the Ecole Normale Sup
 érieure (Paris\, France)\, his Ph.D. degree at the University of Tokyo (J
 apan) and the Université Pierre et Marie Curie (Paris\, France)\, and wor
 ked as a postdoctoral researcher at NTT's Communication Science Laboratori
 es from 2009 to 2011. His research interests are in signal processing and 
 machine learning applied to speech and audio. He has contributed to more t
 han 80 peer-reviewed papers and 20 patents in these fields. He is a founde
 r and chair of the Speech and Audio in the Northeast (SANE) series of work
 shops\, a Senior Member of the IEEE\, and a member of the IEEE Audio and A
 coustic Signal Processing Technical Committee (AASP).
LOCATION:LT6\, Baker Building\, CUED
END:VEVENT
END:VCALENDAR