asaisaio 发表于 2013-1-15 12:15

请问如何调用这个函数提取MFCC参数?(有说明)

= wavread( 'filename.wav' );
...
for i = 1 : framenumber
      将第 i 帧存储至向量 x 中,帧长为 framelength;
      【调用 melfcc 函数提取第 i 帧(即x)的12维特征参数;】
end
-------------------------------
我的问题是,我看不懂下面这个函数说明,因此不会使用这个现成的 melfcc 函数,导致不会写上面那条函数调用语句“【调用 melfcc 函数提取第 i 帧(即x)的12维特征参数;】”
-------------------------------
函数说明如下:>> help melfcc
= melfcc(samples, sr[, opts ...])
   Calculate Mel-frequency cepstral coefficients by:
    - take the absolute value of the STFT
    - warp to a Mel frequency scale
    - take the DCT of the log-Mel-spectrum
    - return the first <ncep> components
   This version allows a lot of options to be controlled, as optional
   'name', value pairs from the 3rd argument on: (defaults in parens)
   'wintime' (0.025): window length in sec
   'hoptime' (0.010): step between successive windows in sec
   'numcep'   (13): number of cepstra to return
   'lifterexp' (0.6): exponent for liftering; 0 = none; < 0 = HTK sin lifter
   'sumpower'    (1): 1 = sum abs(fft)^2; 0 = sum abs(fft)
   'preemph'(0.97): apply pre-emphasis filter (0 = none)
   'dither'      (0): 1 = add offset to spectrum as if dither noise
   'minfreq'   (0): lowest band edge of mel filters (Hz)
   'maxfreq'(4000): highest band edge of mel filters (Hz)
   'nbands'   (40): number of warped spectral bands to use
   'bwidth'    (1.0): width of aud spec filters relative to default
   'dcttype'   (2): type of DCT used - 1 or 2 (or 3 for HTK or 4 for feac)
   'fbtype'('mel'): frequency warp: 'mel','bark','htkmel','fcmel'
   'usecmp'      (0): apply equal-loudness weighting and cube-root compr.
   'modelorder'(0): if > 0, fit a PLP model of this order
   'broaden'   (0): flag to retain the (useless?) first and last bands
   'useenergy'   (0): overwrite C0 with true log energy
The following non-default values nearly duplicate Malcolm Slaney's mfcc
(i.e. melfcc(d,16000,opts...) =~= log(10)*2*mfcc(d*(2^17),16000) )
      'wintime': 0.016
      'lifterexp': 0
      'minfreq': 133.33
      'maxfreq': 6855.6
       'sumpower': 0
The following non-default values nearly duplicate HTK's MFCC
(i.e. melfcc(d,16000,opts...) =~= 2*htkmelfcc(:,])'
   where HTK config has PREEMCOEF = 0.97, NUMCHANS = 20, CEPLIFTER = 22,
   NUMCEPS = 12, WINDOWSIZE = 250000.0, USEHAMMING = T, TARGETKIND = MFCC_0)
      'lifterexp': -22
         'nbands': 20
      'maxfreq': 8000
       'sumpower': 0
         'fbtype': 'htkmel'
      'dcttype': 3


superxjw 发表于 2013-1-15 14:27

看楼主的意思,是要对一个声音文件提取什么参数吧?
页: [1]
查看完整版本: 请问如何调用这个函数提取MFCC参数?(有说明)