source: python/demos/demo_mfcc.py @ 25d0c42

#! /usr/bin/env python

import sys
from aubio import source, pvoc, mfcc
from numpy import vstack, zeros

win_s = 512                 # fft size
hop_s = win_s // 4          # hop size
n_filters = 40              # must be 40 for mfcc
n_coeffs = 13
samplerate = 44100

if len(sys.argv) < 2:
    print("Usage: %s <source_filename>" % sys.argv[0])
    sys.exit(1)

source_filename = sys.argv[1]

samplerate = 0
if len( sys.argv ) > 2: samplerate = int(sys.argv[2])

s = source(source_filename, samplerate, hop_s)
samplerate = s.samplerate
p = pvoc(win_s, hop_s)
m = mfcc(win_s, n_filters, n_coeffs, samplerate)

mfccs = zeros([n_coeffs,])
frames_read = 0
while True:
    samples, read = s()
    spec = p(samples)
    mfcc_out = m(spec)
    mfccs = vstack((mfccs, mfcc_out))
    frames_read += read
    if read < hop_s: break

# do plotting
from numpy import arange
from demo_waveform_plot import get_waveform_plot
from demo_waveform_plot import set_xlabels_sample2time
import matplotlib.pyplot as plt

fig = plt.figure()
plt.rc('lines',linewidth='.8')
wave = plt.axes([0.1, 0.75, 0.8, 0.19])

get_waveform_plot( source_filename, samplerate, block_size = hop_s, ax = wave)
wave.xaxis.set_visible(False)
wave.yaxis.set_visible(False)

all_times = arange(mfccs.shape[0]) * hop_s
n_coeffs = mfccs.shape[1]
for i in range(n_coeffs):
    ax = plt.axes ( [0.1, 0.75 - ((i+1) * 0.65 / n_coeffs),  0.8, 0.65 / n_coeffs], sharex = wave )
    ax.xaxis.set_visible(False)
    ax.yaxis.set_visible(False)
    ax.plot(all_times, mfccs.T[i])

# add time to the last axis
set_xlabels_sample2time( ax, frames_read, samplerate) 

#plt.ylabel('spectral descriptor value')
ax.xaxis.set_visible(True)
wave.set_title('MFCC for %s' % source_filename)
plt.show()