Why Deep Neural Networks Are Promising for Speech Recognition

Add to your list(s) Download to your calendar using vCal

• Dr Dong Yu - Microsoft Research
• Monday 02 July 2012, 11:00-12:30
• Lecture Room 4.

If you have a question about this talk, please contact .

Recently we have proposed and developed the context-dependent deep neural network (DNN) hidden Markov model (CD-DNN-HMM) for large vocabulary 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 conventional 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.

This talk is part of the Why Deep Neural Networks Are Promising for Speech Recognition series.

This talk is included in these lists:

• Why Deep Neural Networks Are Promising for Speech Recognition
• Lecture Room 4

Note that ex-directory lists are not shown.