1


Hello, guys. (Is it OK that start this sentence?)

I tried to simulate with HTK tool that voice(word) recognition.
And I have *.wav files.
Some files have 16KHz sampling rate, some files have 44.1KHz sampling rate.

And I make mfcc file about each sampling rate.
But, I make HMM model using all(16KHz's and 44.1KHz's) mfcc files.

voice_16KHz.wav -> voice_1.mfcc
voice_44.1KHz.wav -> voice_2.mfcc
make hmm_model using voice_1.mfcc and voice_2.mfcc

Is it OK that make HMM model with mixing different sampling rate?

I should know surely information, not suggestion.

Thanks for reading.

Won Hyoung Lee
  • 383
  • 2
  • 14

1 Answers1

1

I will suggest you to go for one sampling rate only. It will work but the Accuracy will change and also you need to change the configuration details in MFCC config file. Downgrade 44.1KHz files to 16KHz it's very easy.

Nilkanth Shirodkar
  • 5
  • 3