def getSpanOffsetByChannel(self, mfcc):
output = []
for i in range(len(mfcc[:, 1])):
span = max(mfcc[i, :].ravel()) - min(mfcc[i, :].ravel())
offset = (span / 2.0) - max(mfcc[i, :].ravel())
output.append((span, offset))
return output
if __name__ == "__main__":
import numpy as np
testFile1 = "../tests/testSong1Original.wav"
testFile2 = "../tests/testSong2Synth.wav"
h = Hearing(tutorsong=None)
mfcc1 = h.calcMfcc(testFile1)
mfcc2 = h.calcMfcc(testFile2)
mfccZero = np.zeros([3, 22])
mfccMin = np.full([3, 22], max(mfcc1.ravel()))
mfccRandom = (np.random.rand(3, 23) * 2 - 1) * 150
mfccRandom2 = (np.random.rand(3, 23) * 2 - 1) * 150
tutorsong = np.concatenate((mfcc1, mfcc1, mfcc1, mfcc1, mfcc1), axis=1)
syllablesMfccs = [
mfcc1,
mfcc2,
mfccZero,
mfccRandom,
from architecture.components.hearing import Hearing
import numpy as np
from sklearn.decomposition import PCA
if __name__ == "__main__":
# testfiles = [
# "./testSong1Original.wav",
# "./testSong2Synth.wav"
# ]
testfiles = []
for i in range(12):
testfiles.append("./testpattern-{i}.wav".format(i=i))
h = Hearing(channels=12)
dataTmp = []
for f in testfiles:
mfcc = h.calcMfcc(f)
dataTmp.append(mfcc.T)
data = np.concatenate(dataTmp)
print "data shape:",data.shape
pca = PCA(n_components=12)
pca.fit(data)
print(pca.explained_variance_ratio_)
[0.1, 0.1, 0.1, 0.1, 100, -10, 0.1, 0.1, 0.1, 100, 0.25],
[10, 10, 10, 10, 10, -10, 10, 10, 10, 10, 0.25],
[1, 1, 1, 1, 1, -1, -1, -1, -1, -1, 0.25],
[0.0001, 0.0001, 0.0001, 0.0001, 0.0001, -0.0001, 0.0001, 0.0001, 0.0001, 0.0001, 0.25]
]
testfiles = [
"./testpattern-0.wav",
"./testpattern-2.wav",
"./testpattern-3.wav",
"./testpattern-4.wav",
"./testpattern-6.wav",
"./testpattern-7.wav"
]
h = Hearing(tutorsong=None)
mfccs = []
for tf in testfiles:
mfcc = h.calcMfcc(tf)
mfccs.append(mfcc)
# for mfcc in mfccs:
# print mfcc.shape
trainingDataInput = []
trainingDataOutput = []
for patternIndex in range(len(patterns)):
mfccLen = getMfccLen(patterns[patternIndex][-1])
for i in range(mfccLen):
def outputStream(content):
global output
output.append(content)
ss = SoundSynthesizer(inputStream, outputStream)
ss.synthesize()
d2w = Dat2Wav
sound = d2w.convert(output)
d2w.writeWAV(sound, filehandleTemp, 44100)
print "done synthing, now creating data"
h = Hearing(tutorsong=None)
mfcc = h.calcMfcc(filehandleTemp)
for mfccIndex in range(len(mfcc[1, :])):
patternStr = [str(p) for p in pattern]
filehandleInputs.write(",".join([str(mfccIndex)] + patternStr) + "\n")
mfccStr = [str(m) for m in mfcc[:, mfccIndex]]
filehandleOutputs.write(",".join(mfccStr) + "\n")
os.remove(filehandleTemp)
print "done writing data\n"
filehandleInputs.close()
