def thumbnailWrapper(inputFile, thumbnailWrapperSize):
st_window = 0.5
st_step = 0.5
if not os.path.isfile(inputFile):
raise Exception("Input audio file not found!")
[fs, x] = audioBasicIO.readAudioFile(inputFile)
if fs == -1: # could not read file
return
[A1, A2, B1, B2, Smatrix] = aS.musicThumbnailing(x, fs, st_window, st_step,
thumbnailWrapperSize)
# write thumbnailWrappers to WAV files:
if inputFile.endswith(".wav"):
thumbnailWrapperFileName1 = inputFile.replace(".wav", "_thumb1.wav")
thumbnailWrapperFileName2 = inputFile.replace(".wav", "_thumb2.wav")
if inputFile.endswith(".mp3"):
thumbnailWrapperFileName1 = inputFile.replace(".mp3", "_thumb1.mp3")
thumbnailWrapperFileName2 = inputFile.replace(".mp3", "_thumb2.mp3")
wavfile.write(thumbnailWrapperFileName1, fs, x[int(fs * A1):int(fs * A2)])
wavfile.write(thumbnailWrapperFileName2, fs, x[int(fs * B1):int(fs * B2)])
print("1st thumbnailWrapper (stored in file {0:s}): {1:4.1f}sec" \
" -- {2:4.1f}sec".format(thumbnailWrapperFileName1, A1, A2))
print("2nd thumbnailWrapper (stored in file {0:s}): {1:4.1f}sec" \
" -- {2:4.1f}sec".format(thumbnailWrapperFileName2, B1, B2))
# Plot self-similarity matrix:
fig = plt.figure()
ax = fig.add_subplot(111, aspect="auto")
plt.imshow(Smatrix)
# Plot best-similarity diagonal:
Xcenter = (A1 / st_step + A2 / st_step) / 2.0
Ycenter = (B1 / st_step + B2 / st_step) / 2.0
e1 = matplotlib.patches.Ellipse((Ycenter, Xcenter),
thumbnailWrapperSize * 1.4, 3, angle=45,
linewidth=3, fill=False)
ax.add_patch(e1)
plt.plot([B1/ st_step, Smatrix.shape[0]], [A1/ st_step, A1/ st_step], color="k",
linestyle="--", linewidth=2)
plt.plot([B2/ st_step, Smatrix.shape[0]], [A2/ st_step, A2/ st_step], color="k",
linestyle="--", linewidth=2)
plt.plot([B1/ st_step, B1/ st_step], [A1/ st_step, Smatrix.shape[0]], color="k",
linestyle="--", linewidth=2)
plt.plot([B2/ st_step, B2/ st_step], [A2/ st_step, Smatrix.shape[0]], color="k",
linestyle="--", linewidth=2)
plt.xlim([0, Smatrix.shape[0]])
plt.ylim([Smatrix.shape[1], 0])
ax.yaxis.set_label_position("right")
ax.yaxis.tick_right()
plt.xlabel("frame no")
plt.ylabel("frame no")
plt.title("Self-similarity matrix")
plt.show()
def thumbnailWrapper(inputFile, thumbnailWrapperSize):
st_window = 0.5
st_step = 0.5
if not os.path.isfile(inputFile):
raise Exception("Input audio file not found!")
[fs, x] = audioBasicIO.readAudioFile(inputFile)
if fs == -1: # could not read file
return
[A1, A2, B1, B2, Smatrix] = aS.musicThumbnailing(x, fs, st_window, st_step,
thumbnailWrapperSize)
# write thumbnailWrappers to WAV files:
if inputFile.endswith(".wav"):
thumbnailWrapperFileName1 = inputFile.replace(".wav", "_thumb1.wav")
thumbnailWrapperFileName2 = inputFile.replace(".wav", "_thumb2.wav")
if inputFile.endswith(".mp3"):
thumbnailWrapperFileName1 = inputFile.replace(".mp3", "_thumb1.mp3")
thumbnailWrapperFileName2 = inputFile.replace(".mp3", "_thumb2.mp3")
wavfile.write(thumbnailWrapperFileName1, fs, x[int(fs * A1):int(fs * A2)])
wavfile.write(thumbnailWrapperFileName2, fs, x[int(fs * B1):int(fs * B2)])
print("1st thumbnailWrapper (stored in file {0:s}): {1:4.1f}sec" \
" -- {2:4.1f}sec".format(thumbnailWrapperFileName1, A1, A2))
print("2nd thumbnailWrapper (stored in file {0:s}): {1:4.1f}sec" \
" -- {2:4.1f}sec".format(thumbnailWrapperFileName2, B1, B2))
# Plot self-similarity matrix:
fig = plt.figure()
ax = fig.add_subplot(111, aspect="auto")
plt.imshow(Smatrix)
# Plot best-similarity diagonal:
Xcenter = (A1 / st_step + A2 / st_step) / 2.0
Ycenter = (B1 / st_step + B2 / st_step) / 2.0
e1 = matplotlib.patches.Ellipse((Ycenter, Xcenter),
thumbnailWrapperSize * 1.4, 3, angle=45,
linewidth=3, fill=False)
ax.add_patch(e1)
plt.plot([B1/ st_step, Smatrix.shape[0]], [A1/ st_step, A1/ st_step], color="k",
linestyle="--", linewidth=2)
plt.plot([B2/ st_step, Smatrix.shape[0]], [A2/ st_step, A2/ st_step], color="k",
linestyle="--", linewidth=2)
plt.plot([B1/ st_step, B1/ st_step], [A1/ st_step, Smatrix.shape[0]], color="k",
linestyle="--", linewidth=2)
plt.plot([B2/ st_step, B2/ st_step], [A2/ st_step, Smatrix.shape[0]], color="k",
linestyle="--", linewidth=2)
plt.xlim([0, Smatrix.shape[0]])
plt.ylim([Smatrix.shape[1], 0])
ax.yaxis.set_label_position("right")
ax.yaxis.tick_right()
plt.xlabel("frame no")
plt.ylabel("frame no")
plt.title("Self-similarity matrix")
plt.show()
def extractFeatures(filePath,
fileName,
music_genre=None,
window=0.05,
step=0.05,
thumbnailSize=20,
playDuration=20):
music = {}
music["fileName"] = fileName
music["filePath"] = filePath
music["genre"] = music_genre
#music["fileInfo"]=[]
[fs, x] = pyab.readAudioFile(filePath + fileName)
if thumbnailSize is not None:
[A1, A2, B1, B2, S] = pyas.musicThumbnailing(x, fs, thumbnailSize)
B = A1
E = B + playDuration
audio = AudioSegment.from_file(filePath + fileName)
music["audio"] = audio[int(1000 * B):int(1000 * E)]
else:
B = 0
E = B + playDuration
audio = AudioSegment.from_file(filePath + fileName)
music["audio"] = audio[int(1000 * B):int(1000 * E)]
x = pyab.stereo2mono(x)
x = x[int(fs * B):int(fs * E)]
music["thumbNail"] = (B, E)
music["fileData"] = x
music["stFeatures"] = pyaf.stFeatureExtraction(x, fs, window * fs,
step * fs)
music["FrameRate"] = fs
#music["classifierResult"] = None
#music["UserResult"] = None
return music
"""!
@brief Example 30
@details: Music thumbnailing example
@author Theodoros Giannakopoulos {[email protected]}
"""
import os, readchar, matplotlib.pyplot as plt, matplotlib
from pyAudioAnalysis.audioBasicIO import readAudioFile, stereo2mono
from pyAudioAnalysis.audioSegmentation import musicThumbnailing
if __name__ == '__main__':
# read signal and get normalized segment features:
input_file = "../data/song2.mp3"
fs, x = readAudioFile(input_file)
x = stereo2mono(x)
win = 0.5
[A1, A2, B1, B2, Smatrix] = musicThumbnailing(x, fs, win, win, 20)
os.system("avconv -i {} -ss {} -t {} thumb1.wav "
"-loglevel panic -y".format(input_file, A1, A2 - A1))
os.system("avconv -i {} -ss {} -t {} thumb2.wav "
"-loglevel panic -y".format(input_file, B1, B2 - B1))
print("Playing thumbnail 1")
os.system("play thumb1.wav -q")
readchar.readchar()
print("Playing thumbnail 2")
os.system("play thumb2.wav -q")
fig = plt.figure()
ax = fig.add_subplot(111, aspect="auto")
plt.imshow(Smatrix)
# Plot best-similarity diagonal:
Xcenter = (A1 / win + A2 / win) / 2.0
Ycenter = (B1 / win + B2 / win) / 2.0
def main(argv):
if argv[1] == "-shortTerm":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("snakehit.wav")
duration = x.shape[0] / float(Fs)
t1 = time.clock()
F = audioFeatureExtraction.stFeatureExtraction(
x, Fs, 0.050 * Fs, 0.050 * Fs)
t2 = time.clock()
perTime1 = duration / (t2 - t1)
print "short-term feature extraction: {0:.1f} x realtime".format(
perTime1)
elif argv[1] == "-classifyFile":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("snakehit.wav")
duration = x.shape[0] / float(Fs)
t1 = time.clock()
aT.fileClassification("snakehit.wav", "svmSM", "svm")
t2 = time.clock()
perTime1 = duration / (t2 - t1)
print "Mid-term feature extraction + classification \t {0:.1f} x realtime".format(
perTime1)
elif argv[1] == "-mtClassify":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("snakehit.wav")
duration = x.shape[0] / float(Fs)
t1 = time.clock()
[flagsInd, classesAll,
acc] = aS.mtFileClassification("snakehit.wav", "svmSM", "svm",
False, '')
t2 = time.clock()
perTime1 = duration / (t2 - t1)
print "Fix-sized classification - segmentation \t {0:.1f} x realtime".format(
perTime1)
elif argv[1] == "-hmmSegmentation":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("snakehit.wav")
duration = x.shape[0] / float(Fs)
t1 = time.clock()
aS.hmmSegmentation('snakehit.wav', 'hmmRadioSM', False, '')
t2 = time.clock()
perTime1 = duration / (t2 - t1)
print "HMM-based classification - segmentation \t {0:.1f} x realtime".format(
perTime1)
elif argv[1] == "-silenceRemoval":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("snakehit.wav")
duration = x.shape[0] / float(Fs)
t1 = time.clock()
[Fs, x] = audioBasicIO.readAudioFile("snakehit.wav")
segments = aS.silenceRemoval(x,
Fs,
0.050,
0.050,
smoothWindow=1.0,
Weight=0.3,
plot=False)
t2 = time.clock()
perTime1 = duration / (t2 - t1)
print "Silence removal \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-thumbnailing":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("scottish.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
[A1, A2, B1, B2,
Smatrix] = aS.musicThumbnailing(x1, Fs1, 1.0, 1.0,
15.0) # find thumbnail endpoints
t2 = time.clock()
perTime1 = duration1 / (t2 - t1)
print "Thumbnail \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-diarization-noLDA":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("snakehit.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
aS.speakerDiarization("snakehit.wav", 4, LDAdim=0, PLOT=False)
t2 = time.clock()
perTime1 = duration1 / (t2 - t1)
print "Diarization \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-diarization-LDA":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("snakehit.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
aS.speakerDiarization("snakehit.wav", 4, PLOT=False)
t2 = time.clock()
perTime1 = duration1 / (t2 - t1)
print "Diarization \t {0:.1f} x realtime".format(perTime1)
def main(argv):
if argv[1] == "-shortTerm":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
F = audioFeatureExtraction.stFeatureExtraction(x, Fs, 0.050*Fs, 0.050*Fs);
t2 = time.clock()
perTime1 = duration / (t2-t1); print "short-term feature extraction: {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-classifyFile":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
aT.fileClassification("diarizationExample.wav", "svmSM","svm")
t2 = time.clock()
perTime1 = duration / (t2-t1); print "Mid-term feature extraction + classification \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-mtClassify":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
[flagsInd, classesAll, acc] = aS.mtFileClassification("diarizationExample.wav", "svmSM", "svm", False, '')
t2 = time.clock()
perTime1 = duration / (t2-t1); print "Fix-sized classification - segmentation \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-hmmSegmentation":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
aS.hmmSegmentation('diarizationExample.wav', 'hmmRadioSM', False, '')
t2 = time.clock()
perTime1 = duration / (t2-t1); print "HMM-based classification - segmentation \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-silenceRemoval":
for i in range(nExp):
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
duration = x.shape[0] / float(Fs)
t1 = time.clock()
[Fs, x] = audioBasicIO.readAudioFile("diarizationExample.wav");
segments = aS.silenceRemoval(x, Fs, 0.050, 0.050, smoothWindow = 1.0, Weight = 0.3, plot = False)
t2 = time.clock()
perTime1 = duration / (t2-t1); print "Silence removal \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-thumbnailing":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("scottish.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
[A1, A2, B1, B2, Smatrix] = aS.musicThumbnailing(x1, Fs1, 1.0, 1.0, 15.0) # find thumbnail endpoints
t2 = time.clock()
perTime1 = duration1 / (t2-t1); print "Thumbnail \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-diarization-noLDA":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("diarizationExample.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
aS.speakerDiarization("diarizationExample.wav", 4, LDAdim = 0, PLOT = False)
t2 = time.clock()
perTime1 = duration1 / (t2-t1); print "Diarization \t {0:.1f} x realtime".format(perTime1)
elif argv[1] == "-diarization-LDA":
for i in range(nExp):
[Fs1, x1] = audioBasicIO.readAudioFile("diarizationExample.wav")
duration1 = x1.shape[0] / float(Fs1)
t1 = time.clock()
aS.speakerDiarization("diarizationExample.wav", 4, PLOT = False)
t2 = time.clock()
perTime1 = duration1 / (t2-t1); print "Diarization \t {0:.1f} x realtime".format(perTime1)