In file ../include/sigpr/EST_sigpr_frame.h:

void fbank2melcep

(const EST_FVector &fbank_vec,
  EST_FVector &mfcc,
  const float liftering_parameter,
  const bool include_c0 = false)

Compute the dicrete cosine transform of log Mel-scale filter bank output to get the Mel cepstral coeffecients for a frame of speech.

Documentation

Compute the dicrete cosine transform of log Mel-scale filter bank output to get the Mel cepstral coeffecients for a frame of speech. Optional liftering (filtering in the cepstral domain) can be applied to normalise the magnitudes of the coefficients. This is useful because, typically, the higher order cepstral coefficients are significantly smaller than the lower ones and it is often desirable to normalise the means and variances across coefficients.

The lifter (cepstral filter) used is:


A typical value of L used in speech recognition is 22. A value of L=0 is taken to mean no liftering. This is equivalent to L=1.

See Also:
sig2fft
fft2fbank
sig2fbank

Alphabetic index HTML hierarchy of classes or Java


This page is part of the Edinburgh Speech Tools Library documentation
Copyright University of Edinburgh 1997
Contact: speech_tools@cstr.ed.ac.uk