How visual speech recognition is done using CNN and LSTM in Matlab?

In ViSUAL ASR, both audio and video inputs are there to recognize isolated words.I have seperated audio and video frames. How to process it using CNN & LSTM in Matlab

Answer 1

[Swetha Polemoni]

Hi

It is my understanding that you wanted to know how to work/ use LSTM and CNN in Matlab. The following documentations might help you.

Specify Layers of Convolutional Neural Network

Learn About Convolutional Neural Networks

Long Short-Term Memory Networks

[Shilpa Sonawane]

Thank you sir

Answer 2

[David Willingham]

Hi Shilpa,

Here is a good starting page to learning about how Deep Learning can be used in Audio Processing:

https://www.mathworks.com/help/deeplearning/audio-processing-using-deep-learning.html

David

[Shilpa Sonawane]

Thank you sir