tango2 / tools /mix.py
hungchiayu1
initial commit
ffead1e
import numpy as np
def a_weight(fs, n_fft, min_db=-80.0):
freq = np.linspace(0, fs // 2, n_fft // 2 + 1)
freq_sq = np.power(freq, 2)
freq_sq[0] = 1.0
weight = 2.0 + 20.0 * (2 * np.log10(12194) + 2 * np.log10(freq_sq)
- np.log10(freq_sq + 12194 ** 2)
- np.log10(freq_sq + 20.6 ** 2)
- 0.5 * np.log10(freq_sq + 107.7 ** 2)
- 0.5 * np.log10(freq_sq + 737.9 ** 2))
weight = np.maximum(weight, min_db)
return weight
def compute_gain(sound, fs, min_db=-80.0, mode="A_weighting"):
if fs == 16000:
n_fft = 2048
elif fs == 44100:
n_fft = 4096
else:
raise Exception("Invalid fs {}".format(fs))
stride = n_fft // 2
gain = []
for i in range(0, len(sound) - n_fft + 1, stride):
if mode == "RMSE":
g = np.mean(sound[i: i + n_fft] ** 2)
elif mode == "A_weighting":
spec = np.fft.rfft(np.hanning(n_fft + 1)[:-1] * sound[i: i + n_fft])
power_spec = np.abs(spec) ** 2
a_weighted_spec = power_spec * np.power(10, a_weight(fs, n_fft) / 10)
g = np.sum(a_weighted_spec)
else:
raise Exception("Invalid mode {}".format(mode))
gain.append(g)
gain = np.array(gain)
gain = np.maximum(gain, np.power(10, min_db / 10))
gain_db = 10 * np.log10(gain)
return gain_db
def mix(sound1, sound2, r, fs):
gain1 = np.max(compute_gain(sound1, fs)) # Decibel
gain2 = np.max(compute_gain(sound2, fs))
t = 1.0 / (1 + np.power(10, (gain1 - gain2) / 20.) * (1 - r) / r)
sound = ((sound1 * t + sound2 * (1 - t)) / np.sqrt(t ** 2 + (1 - t) ** 2))
return sound