I think that this approach should work rather well (I did very simillar project few years ago). Things you might consider:
- You probably might want to use pre-emphasis filter on a signal.
- In addition to MFCC features you can also include $\Delta$ and $\Delta\Delta$. Some theory can be found for example here: click!
- Comparing against more templates in my case largely improved recognition rate. I think that the easiest way do so is by using k-NN algorithm on distances returned from DWT.
Good luck!