shithub: aubio

ref: 04281508709213d63fb61446b22fa418bb056975
dir: /python/demos/demo_pitch.py/

View raw version
#! /usr/bin/env python

import sys
from aubio import source, pitch, freqtomidi

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

filename = sys.argv[1]

downsample = 1
samplerate = 44100 / downsample
if len( sys.argv ) > 2: samplerate = int(sys.argv[2])

win_s = 4096 / downsample # fft size
hop_s = 512  / downsample # hop size

s = source(filename, samplerate, hop_s)
samplerate = s.samplerate

tolerance = 0.8

pitch_o = pitch("yin", win_s, hop_s, samplerate)
pitch_o.set_unit("freq")
pitch_o.set_tolerance(tolerance)

pitches = []
confidences = []

# total number of frames read
total_frames = 0
while True:
    samples, read = s()
    pitch = pitch_o(samples)[0]
    #pitch = int(round(pitch))
    confidence = pitch_o.get_confidence()
    #if confidence < 0.8: pitch = 0.
    print "%f %f %f" % (total_frames / float(samplerate), pitch, confidence)
    pitches += [pitch]
    confidences += [confidence]
    total_frames += read
    if read < hop_s: break

if 0: sys.exit(0)

#print pitches
from numpy import array, ma
import matplotlib.pyplot as plt
from demo_waveform_plot import get_waveform_plot, set_xlabels_sample2time

skip = 1

pitches = array(pitches[skip:])
confidences = array(confidences[skip:])
times = [t * hop_s for t in range(len(pitches))]

fig = plt.figure()
ax1 = fig.add_subplot(311)
ax1 = get_waveform_plot(filename, samplerate = samplerate, block_size = hop_s, ax = ax1)
ax1.set_xticklabels([])

def array_from_text_file(filename, dtype = 'float'):
    import os.path
    from numpy import array
    filename = os.path.join(os.path.dirname(__file__), filename)
    return array([line.split() for line in open(filename).readlines()],
        dtype = dtype)

ax2 = fig.add_subplot(312, sharex = ax1)
import sys, os.path
ground_truth = os.path.splitext(filename)[0] + '.f0.Corrected'
if os.path.isfile(ground_truth):
    ground_truth = array_from_text_file(ground_truth)
    true_freqs = ground_truth[:,2]
    true_freqs = ma.masked_where(true_freqs < 2, true_freqs)
    true_times = float(samplerate) * ground_truth[:,0]
    ax2.plot(true_times, true_freqs, 'r')
    ax2.axis( ymin = 0.9 * true_freqs.min(), ymax = 1.1 * true_freqs.max() )
# plot raw pitches
ax2.plot(times, pitches, '--g')
# plot cleaned up pitches
cleaned_pitches = pitches
#cleaned_pitches = ma.masked_where(cleaned_pitches < 0, cleaned_pitches)
#cleaned_pitches = ma.masked_where(cleaned_pitches > 120, cleaned_pitches)
cleaned_pitches = ma.masked_where(confidences < tolerance, cleaned_pitches)
ax2.plot(times, cleaned_pitches, '.-')
#ax2.axis( ymin = 0.9 * cleaned_pitches.min(), ymax = 1.1 * cleaned_pitches.max() )
#ax2.axis( ymin = 55, ymax = 70 )
ax2.set_xticklabels([])

# plot confidence
ax3 = fig.add_subplot(313, sharex = ax1)
# plot the confidence
ax3.plot(times, confidences)
# draw a line at tolerance
ax3.plot(times, [tolerance]*len(confidences))
ax3.axis( xmin = times[0], xmax = times[-1])
plt.show()
set_xlabels_sample2time(ax3, times[-1], samplerate)
#plt.savefig(os.path.basename(filename) + '.png', dpi=200)