BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep learning for automatically assessing the pronunciation of non
 -native English speakers - Kostas Kyriakopoulos\, CUED\, University of Cam
 bridge
DTSTART:20181026T110000Z
DTEND:20181026T120000Z
UID:TALK109621@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:In this talk\, I will present my work on automatically charact
 erizing the pronunciation of non-native English speakers based on spontane
 ous utterances. I will begin by defining what we mean by pronunciation and
  the challenges presented by spontaneous\, as opposed to read-aloud\, spee
 ch. I will explore two systems based on distances between phones: a two-st
 age system using K-L divergence between Gaussian models as an input to a D
 NN\, and an end-to-end system using Siamese LSTMs with attention over the 
 hidden representations. It will be seen how both systems can predict human
 -assigned grade\, as well as speaker L1 and country of origin\, and how th
 eir representations can be interpreted. Finally\, I will discuss my approa
 ch to the detection of individual pronunciation errors and how it relates 
 to the auto-marking system.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR