Book Image

Rapid BeagleBoard Prototyping with MATLAB and Simulink

Book Image

Rapid BeagleBoard Prototyping with MATLAB and Simulink

Overview of this book

As an open source embedded single-board computer with many standard interfaces, Beagleboard is ideal for building embedded audio/video systems to realize your practical ideas. The challenge is how to design and implement a good digital processing algorithm on Beagleboard quickly and easily without intensive low-level coding. Rapid BeagleBoard Prototyping with MATLAB and Simulink is a practical, hands-on guide providing you with a number of clear, step-by-step exercises which will help you take advantage of the power of Beagleboard and give you a good grounding in rapid prototyping techniques for your audio/video applications. Rapid BeagleBoard Prototyping with MATLAB and Simulink looks at rapid prototyping and how to apply these techniques to your audio/video applications with Beagleboard quickly and painlessly without intensive manual low-level coding. It will take you through a number of clear, practical recipes that will help you to take advantage of both the Beagleboard hardware platform and Matlab/Simulink signal processing. We will also take a look at building S-function blocks that work as hardware drivers and interfaces for Matlab/Simulink. This gives you more freedom to explore the full range of advantages provided by Beagleboard. By the end of this book, you will have a clear idea about Beagleboard and Matlab/Simulink rapid prototyping as well as how to develop voice recognition systems, motion detection systems with I/O access, and serial communication for your own applications such as a smart home.
Table of Contents (15 chapters)
Rapid BeagleBoard Prototyping with MATLAB and Simulink
Credits
About the Authors
About the Reviewers
www.PacktPub.com
Preface
Index

Feature extraction


We first look at feature extraction, which is a common block shared by both pattern analysis for training and pattern matching for recognition.

Various kinds of audio features have been proposed for voice recognition, including linear predictive coding (LPC), cepstral coefficients, spectral coefficients, and so on. The Mel-Frequency Cepstral Coefficients (MFCC) are probably the most popular at present due to their simplicity and pretty good performance. In this chapter, we are using the MFCC features and associated feature-extraction techniques to build a demonstrative system, as we focus on the demonstration of rapid prototyping. Obviously, a voice recognition system may use a combination of different kinds of features for better recognition performance.

MFCC is based on the fact that the human perception system has a non-linear frequency response to sounds. The frequency response of human's ear works like a band of filters spaced linearly at low frequencies and logarithmically...