Going from an MFCC coefficient to Hz range?

1. How many MFCC coefficients should I use?
2. What is the output of MFCC?
3. What is hop length in MFCC?

How many MFCC coefficients should I use?

In practice, the first 8–13 MFCC coefficients are used to represent the shape of the spectrum. However, some applications require more higher-order coefficients to capture pitch and tone information. For example, in Chinese speech recognition up to 20 cepstral coefficients may be beneficial [130].

What is the output of MFCC?

The output after applying MFCC is a matrix having feature vectors extracted from all the frames. In this output matrix the rows represent the corresponding frame numbers and columns represent corresponding feature vector coefficients [1-4]. Finally this output matrix is used for classification process.

What is hop length in MFCC?

mfcc has two arguments (which actually pass through to the underlying stft). win_length is the number of samples included in each time frame; it defaults to 2048, or ~93ms at 22 kHz SR. hop_length is the number of samples between successive windows; its default is 512, or the 23 ms you calculated.