MFCC - Significance of number of features

1. How many MFCC should I use?
2. How many features are there in MFCC?
3. What is the significance of MFCC?
4. How many MFCC coefficients are there?

How many MFCC should I use?

So how many MFCC's do we want to calculate? HTK by default uses 12 and in most applications it is more than enough. In general we don't want too many coefficients because: It's all about reducing the dimensionality of our feature space.

How many features are there in MFCC?

MFCC has 39 features.

What is the significance of MFCC?

MFCCs are commonly used as features in speech recognition systems, such as the systems which can automatically recognize numbers spoken into a telephone. MFCCs are also increasingly finding uses in music information retrieval applications such as genre classification, audio similarity measures, etc.

How many MFCC coefficients are there?

Traditional MFCC systems use only 8–13 cepstral coefficients. The zeroth coefficient is often excluded since it represents the average log-energy of the input signal, which only carries little speaker-specific information.