Adding noise, Wiener Filtering, and PESQ working
This commit is contained in:
parent
50a5e57e18
commit
b2dd75319f
@ -0,0 +1,82 @@
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
import scipy.signal
|
||||
from scipy.io import wavfile
|
||||
import sounddevice as sd
|
||||
import random
|
||||
from pesq import pesq
|
||||
|
||||
|
||||
|
||||
SIGNAL_PATH = "speechfiles/sp01.wav"
|
||||
NOISE_PATH = "noisefiles/white.dat"
|
||||
|
||||
|
||||
# Scale the signal to the range [-1,1]
|
||||
def normalize_signal(signal):
|
||||
min_amp = np.min(signal)
|
||||
normalized_signal = signal - min_amp
|
||||
max_amp = np.max(normalized_signal)
|
||||
normalized_signal *= 2.0/max_amp
|
||||
normalized_signal -= 1
|
||||
return normalized_signal
|
||||
|
||||
|
||||
# Load an audio file from disk
|
||||
def load_audiofile(path):
|
||||
sound_data = []
|
||||
sample_rate = 8000
|
||||
# Load .dat files as sound files sampled at 8[kHz]
|
||||
if path[-3:] == "dat":
|
||||
with open(path, "r") as sound_file:
|
||||
sound_data_strings = sound_file.readlines()
|
||||
for data_string in sound_data_strings:
|
||||
sound_data.append(eval(data_string.strip()))
|
||||
sound_data = np.array(sound_data, dtype=np.float64)
|
||||
elif path[-3:] == "wav":
|
||||
sample_rate, sound_data = wavfile.read(path)
|
||||
# Make sure it is nparray of floats (trust me bro, normalizing yells at you if its ints)
|
||||
sound_data = np.array(sound_data, dtype=np.float64)
|
||||
return sample_rate, sound_data
|
||||
|
||||
|
||||
# Add noise to a signal with a desired SNR
|
||||
def add_noise(signal, noise, snr):
|
||||
len_signal = len(signal)
|
||||
len_noise = len(noise)
|
||||
|
||||
# Get a random crop of the noise to match the length of the signal
|
||||
noise_crop_start = random.randrange(len_noise-len_signal)
|
||||
noise_crop = noise[noise_crop_start:noise_crop_start+len_signal]
|
||||
|
||||
# Calculate the power of the signal and noise
|
||||
noise_power = np.linalg.norm(noise_crop, 2)
|
||||
signal_power = np.linalg.norm(signal, 2)
|
||||
|
||||
# Adjust the noise level to match desired SNR
|
||||
u = 10**(snr/20)
|
||||
desired_noise_power = signal_power/u
|
||||
ratio = desired_noise_power / noise_power
|
||||
noise_crop *= ratio
|
||||
|
||||
noisy_signal = signal + noise_crop
|
||||
return noisy_signal
|
||||
|
||||
|
||||
def main():
|
||||
signal_sample_rate, signal_data = load_audiofile(SIGNAL_PATH)
|
||||
noise_sample_rate, noise_data = load_audiofile(NOISE_PATH)
|
||||
assert signal_sample_rate == noise_sample_rate, "Signal and noise sampling rates didn't match."
|
||||
sample_rate = signal_sample_rate
|
||||
|
||||
noisy_signal = add_noise(signal_data, noise_data, 0)
|
||||
filtered_signal = scipy.signal.wiener(noisy_signal)
|
||||
|
||||
print(pesq(sample_rate, signal_data, noisy_signal, mode='nb'))
|
||||
print(pesq(sample_rate, signal_data, filtered_signal, mode='nb'))
|
||||
#sd.play(normalize_signal(noisy_signal), samplerate=sample_rate, blocking=True)
|
||||
#sd.play(normalize_signal(filtered_signal), samplerate=sample_rate, blocking=True)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
@ -1,41 +0,0 @@
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
import scipy.signal
|
||||
import sounddevice as sd
|
||||
|
||||
|
||||
|
||||
SOUND_PATH = "noisefiles/train.dat"
|
||||
|
||||
|
||||
def normalize_signal(signal):
|
||||
min_amp = np.min(signal)
|
||||
normalized_signal = signal - min_amp
|
||||
max_amp = np.max(normalized_signal)
|
||||
normalized_signal *= 2/max_amp
|
||||
normalized_signal -= 1
|
||||
return normalized_signal
|
||||
|
||||
|
||||
def load_audiofile(path):
|
||||
sound_data = []
|
||||
sample_rate = 8000
|
||||
if path[-3:] == "dat":
|
||||
with open(SOUND_PATH, "r") as sound_file:
|
||||
sound_data_strings = sound_file.readlines()
|
||||
for data_string in sound_data_strings:
|
||||
sound_data.append(eval(data_string.strip()))
|
||||
sound_data = np.array(sound_data)
|
||||
elif path[-3:] == "wav":
|
||||
sample_rate, sound_data = wavfile.read(path)
|
||||
return sample_rate, sound_data
|
||||
|
||||
|
||||
def main():
|
||||
sample_rate, sound_data = load_audiofile(SOUND_PATH)
|
||||
print(sample_rate)
|
||||
sd.play(normalize_signal(sound_data), samplerate=sample_rate, blocking=True)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
Loading…
Reference in New Issue
Block a user