def audio_analysis (filename):
print filename
downsample = 1
samplerate = 44100 / downsample
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 = []
time_stamp=[]
# total number of frames read
total_frames = 0
while True:
samples, read = s()
pitch1 = 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), pitch1, confidence)
time_stamp+=[(total_frames/float(samplerate))]
pitches += [pitch1]
confidences += [confidence]
total_frames += read
if read < hop_s: break
if 0: sys.exit(0)
#print time_stamp
# Invoking aubiocut to detect when a word of spoken.
sub = subprocess.Popen(['python', 'aubiocut', filename], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
out = sub.communicate()[0]
# Importing Regular Expression Modules for extracting the output[timestamp] of Aubiocut
import re
timestamps=re.findall("\d+.\d+\d+\d+\d+", out)
# print timestamps
extracted_voice=[]
import math
for i in timestamps:
i=float(i)
for j in range(len(time_stamp)):
#Using the floor functions the timestamp is extracted when speakers spoke a word.
temp1=math.floor(i*10)/10
temp2=math.floor((time_stamp[j])*10)/10
#print str(temp1)+ " and "+str(temp2)
# if pitch >10000 then it is considered Noice in our environment.
if temp1==temp2 and pitches[j]<10000.0:
#print "True"+str(j)+pitches[j]
extracted_voice+=[pitches[j]]
# print extracted_voice
avg=0.0
for i in extracted_voice:
avg+=i
avg=avg/(len(extracted_voice))
print "Average Pitch of Extracted Voice: "+ str(avg)
formantf = get_formants(filename)
for i in formantf:
if i != 0:
formantf = i
break
output_final=""
gender=clf.classify([avg])
output_final="Predicted Gender : "+gender+"\n"
age_predict=ageclassify(avg, VocalTractLength(formantf))
output_final=output_final+"And "+age_predict
# print "Gender : "+gender
#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)
# plt.setp(ax1.get_xticklabels(), visible = False)
# ax1.set_xlabel('')
# 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 )
# plt.setp(ax2.get_xticklabels(), visible = False)
# ax2.set_ylabel('f0 (Hz)')
# # 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])
# ax3.set_ylabel('condidence')
# set_xlabels_sample2time(ax3, times[-1], samplerate)
# plt.show()
# #plt.savefig(os.path.basename(filename) + '.svg')
return output_final
def audio_analysis(filename):
print type(filename)
# filename = file_name
downsample = 1
samplerate = 44100 / downsample
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 = []
time_stamp = []
# 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)
time_stamp += [(total_frames / float(samplerate))]
pitches += [pitch]
confidences += [confidence]
total_frames += read
if read < hop_s: break
if 0: sys.exit(0)
#print time_stamp
# Invoking aubiocut to detect when a word of spoken.
sub = subprocess.Popen(['python', 'aubiocut', filename],
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
out = sub.communicate()[0]
# Importing Regular Expression Modules for extracting the output[timestamp] of Aubiocut
import re
timestamps = re.findall("\d+.\d+\d+\d+\d+", out)
print timestamps
extracted_voice = []
import math
for i in timestamps:
i = float(i)
for j in range(len(time_stamp)):
#Using the floor functions the timestamp is extracted when speakers spoke a word.
temp1 = math.floor(i * 10) / 10
temp2 = math.floor((time_stamp[j]) * 10) / 10
#print str(temp1)+ " and "+str(temp2)
# if pitch >10000 then it is considered Noice in our environment.
if temp1 == temp2 and pitches[j] < 10000.0:
#print "True"+str(j)+pitches[j]
extracted_voice += [pitches[j]]
print extracted_voice
avg = 0.0
for i in extracted_voice:
avg += i
avg = avg / (len(extracted_voice))
print "Average Pitch of Extracted Voice: " + str(avg)
gender = clf.classify([avg])
#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)
plt.setp(ax1.get_xticklabels(), visible=False)
ax1.set_xlabel('')
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 )
plt.setp(ax2.get_xticklabels(), visible=False)
ax2.set_ylabel('f0 (Hz)')
# 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])
ax3.set_ylabel('condidence')
set_xlabels_sample2time(ax3, times[-1], samplerate)
plt.show()
#plt.savefig(os.path.basename(filename) + '.svg')
return gender
print extracted_voice
avg=0.0
for i in extracted_voice:
avg+=i
avg=avg/(len(extracted_voice))
print "Average Pitch of Extracted Voice: "+ str(avg)
formantf = get_formants(filename)
for i in formantf:
if i != 0:
formantf = i
break
ageclassify(avg, VocalTractLength(formantf))
clf.classify([avg])
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)
plt.setp(ax1.get_xticklabels(), visible = False)
ax1.set_xlabel('')
def array_from_text_file(filename, dtype = 'float'):
import os.path