Intelligent Information Systems
-
Lecture 19 - IIS for Speech Processing
First page
Back
Continue
Last page
Overview
Graphics
Representing Speech Data
Common transform is the mel-scale
The mel-scale is a log scale
Models human perception
Divides the signal into frequency bands
Returns the log-energy for each frequency band
Tweet
Maintained by Dr Michael J. Watts (
mike.watts.net.nz
).