BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:SpeechBrain: Unifying Speech Technologies and Deep Learning With a
 n Open Source Toolkit - Titouan Parcollet (Avignon University)
DTSTART:20220314T120000Z
DTEND:20220314T130000Z
UID:TALK171587@talks.cam.ac.uk
CONTACT:Dr Jie Pu
DESCRIPTION:*Abstract*: SpeechBrain is a novel open-source speech toolkit 
 natively designed to support various speech and audio processing applicati
 ons. It currently supports a large variety of tasks\, such as speech recog
 nition\, speech translation\, speaker recognition\, speech enhancement\, s
 peech separation\,  spoken language understand\, multi-microphone signal p
 rocessing\, just to name a few. With this presentation\, we will navigate 
 throughout all the design choices\, core details and simple examples makin
 g of SpeechBrain the best speech toolkit out there for open\, accessible\,
  replicable and transparent speech technologies.\n\n*Bio*: Titouan Parcoll
 et is an associate professor in computer science at the Laboratoire Inform
 atique d’Avignon (LIA)\, from Avignon University (FR) and a visiting sch
 olar at the Cambridge Machine Learning Systems Lab from the University of 
 Cambridge (UK). Previously\, he was a senior research associate at the Uni
 versity of Oxford (UK) within the Oxford Machine Learning Systems group. H
 e received his PhD in computer science from the University of Avignon (Fra
 nce) and in partnership with Orkis focusing on quaternion neural networks\
 , automatic speech recognition\, and representation learning. His current 
 work involves efficient speech recognition\, federated learning and self-s
 upervised learning. He is also currently collaborating with the Mila-Quebe
 c AI institute as a co-leader of the SpeechBrain project.\n
LOCATION:Zoom: https://eng-cam.zoom.us/j/81927138251?pwd=TVd3MXliV003dUdYV
 lFwU2NDWGpmdz09
END:VEVENT
END:VCALENDAR