Speech Recognition using HMM and VQ - Code Updates

Hey guys,

I've done some minor changes to the Speech Recognition code that I pushed to github/googlecode couple of years ago. As I received several attention/queries from readers/students all over the world regarding couple of minor bugs within the project, I thought its time ( better late than never :P ) to address them into the code.

Significant changes are on:

- Exception handling
- File handling
- File (recorded WAVE file, VQ codebook, HMM models) save path corrected
- Delta calculation fixed when regression window is less than number of frames ( when a short audio sample is recorded)

I've also uploaded training audio samples for few  words, trained Vector Quantization coebook and trained HMM model file for the words.

If you wish to add/train more words, please use the GUI - "HMM_VQ_Speech_Recognition" class. Just a note, you need to re-train both VQ and HMM for each word that you add.

Code :


Report File (contains both Speech and Speaker recognition)


I hope everyone will benefit from this. Keep coding, keep learning. Please let me know if you see any issues.

Thank you!