def gen_speech_at_mic_stft(phi_ks, source_signals, mic_array_coord, noise_power, fs, fft_size=1024):
"""
generate microphone signals with short time Fourier transform
:param phi_ks: azimuth of the acoustic sources
:param source_signals: speech signals for each arrival angle, one per row
:param mic_array_coord: x and y coordinates of the microphone array
:param noise_power: the variance of the microphone noise signal
:param fs: sampling frequency
:param fft_size: number of FFT bins
:return: y_hat_stft: received (complex) signal at microphones
y_hat_stft_noiseless: the noiseless received (complex) signal at microphones
"""
frame_shift_step = np.int(fft_size / 1.) # half block overlap for adjacent frames
K = source_signals.shape[0] # number of point sources
num_mic = mic_array_coord.shape[1] # number of microphones
# Generate the impulse responses for the array and source directions
impulse_response = gen_far_field_ir(np.reshape(phi_ks, (1, -1), order='F'),
mic_array_coord, fs)
# Now generate all the microphone signals
y = np.zeros((num_mic, source_signals.shape[1] + impulse_response.shape[2] - 1), dtype=np.float32)
for src in xrange(K):
for mic in xrange(num_mic):
y[mic] += fftconvolve(impulse_response[src, mic], source_signals[src])
# Now do the short time Fourier transform
# The resulting signal is M x fft_size/2+1 x number of frames
y_hat_stft_noiseless = \
np.array([pra.stft(signal, fft_size, frame_shift_step, transform=mkl_fft.rfft).T
for signal in y]) / np.sqrt(fft_size)
# Add noise to the signals
y_noisy = y + np.sqrt(noise_power) * np.array(np.random.randn(*y.shape), dtype=np.float32)
# compute sources stft
source_stft = \
np.array([pra.stft(s_loop, fft_size, frame_shift_step, transform=mkl_fft.rfft).T
for s_loop in source_signals]) / np.sqrt(fft_size)
y_hat_stft = \
np.array([pra.stft(signal, fft_size, frame_shift_step, transform=mkl_fft.rfft).T
for signal in y_noisy]) / np.sqrt(fft_size)
return y_hat_stft, y_hat_stft_noiseless, source_stft
评论列表
文章目录
