BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: Why Deep Neural Networks Are Promising for Speech Recognition - D
 r Dong Yu - Microsoft Research
DTSTART:20120702T100000Z
DTEND:20120702T113000Z
UID:TALK38835@talks.cam.ac.uk
CONTACT:29011
DESCRIPTION:Recently we have proposed and developed the context-dependent 
 deep neural network (DNN) hidden Markov model (CD-DNN-HMM) for large vocab
 ulary speech recognition (LVSR) and demonstrated its superior performance 
 on several benchmark tasks. In this talk I will share the observations and
  thoughts we have in understanding why DNNs can be more powerful than the 
 shallow neural networks and why CD-DNN-HMMs can outperform the conventiona
 l CD-GMM-HMM system and earlier ANN/HMM hybrid systems. At the end of the 
 talk I will discuss how CD-DNN-HMM can be further improved to achieve even
  better recognition accuracy. 
LOCATION:Lecture Room 4
END:VEVENT
END:VCALENDAR