def run_phase_vq_example():
def _pre(list_of_data):
# Temporal window setting is crucial! - 512 seems OK for music, 256
# fruit perhaps due to samplerates
n_fft = 256
step = 32
f_r = np.vstack([np.abs(stft(dd, n_fft, step=step, real=False,
compute_onesided=False))
for dd in list_of_data])
return f_r, n_fft, step
def preprocess_train(list_of_data, random_state):
f_r, n_fft, step = _pre(list_of_data)
clusters = copy.deepcopy(f_r)
return clusters
def apply_preprocess(list_of_data, clusters):
f_r, n_fft, step = _pre(list_of_data)
f_clust = f_r
# Nondeterministic ?
memberships, distances = vq(f_clust, clusters)
vq_r = clusters[memberships]
d_k = iterate_invert_spectrogram(vq_r, n_fft, step, verbose=True)
return d_k
random_state = np.random.RandomState(1999)
fs, d = fetch_sample_speech_fruit()
d1 = d[::9]
d2 = d[7::8][:5]
# make sure d1 and d2 aren't the same!
assert [len(di) for di in d1] != [len(di) for di in d2]
clusters = preprocess_train(d1, random_state)
fix_d1 = np.concatenate(d1)
fix_d2 = np.concatenate(d2)
vq_d2 = apply_preprocess(d2, clusters)
wavfile.write("phase_train_no_agc.wav", fs, soundsc(fix_d1))
wavfile.write("phase_vq_test_no_agc.wav", fs, soundsc(vq_d2))
agc_d1, freq_d1, energy_d1 = time_attack_agc(fix_d1, fs, .5, 5)
agc_d2, freq_d2, energy_d2 = time_attack_agc(fix_d2, fs, .5, 5)
agc_vq_d2, freq_vq_d2, energy_vq_d2 = time_attack_agc(vq_d2, fs, .5, 5)
"""
import matplotlib.pyplot as plt
plt.specgram(agc_vq_d2, cmap="gray")
#plt.title("Fake")
plt.figure()
plt.specgram(agc_d2, cmap="gray")
#plt.title("Real")
plt.show()
"""
wavfile.write("phase_train_agc.wav", fs, soundsc(agc_d1))
wavfile.write("phase_test_agc.wav", fs, soundsc(agc_d2))
wavfile.write("phase_vq_test_agc.wav", fs, soundsc(agc_vq_d2))
评论列表
文章目录
