Speech Recognition Java Code - Hidden Markov Model / VQ / MFCC

The is a fork/export from code hosted at https://code.google.com/p/speech-recognition-java-hidden-markov-model-vq-mfcc/

Please refer to git repo by original author at https://github.com/gtiwari333/speech-recognition-java-hidden-markov-model-vq-mfcc for latest changes.

The original is (C)opyright 2012 by Ganesh Tiwari.<br> Changes contributed (C)opyright 2015 Hanns Holger Rutz.<br> Released under the Apache License 2.0.

Original Readme

Uses VQ and HMM codes from OCVolume Project.

You need to record training samples yourself. This can be done from GUI class included in project. The same GUI can be used to train,test the audio samples.

Project Report View Joint Speech and Speaker Recognition System Project Report

If you have any comment and thoughts on the codes, please leave a message at gtiwari333@gmail.com.

Ganesh Tiwari<br> Kathmandu<br> Nepal