65 lines
2.1 KiB
Python
65 lines
2.1 KiB
Python
from scipy.io import wavfile as wav
|
|
import numpy as np
|
|
import sys
|
|
|
|
print("Portfolio Object 2: Adaptive Tone Control")
|
|
|
|
# Contants
|
|
bands = {"low": (0, 300), "mid": (300, 2000), "high": (2000, 20000)}
|
|
|
|
file = "test.wav"
|
|
if len(sys.argv) > 1:
|
|
file = sys.argv[1]
|
|
print("Input file: ", file)
|
|
# Init
|
|
sample_rate, wav_signal = wav.read(file)
|
|
# window_size = 1024
|
|
window_size = len(wav_signal)
|
|
fft_values = np.fft.fft(wav_signal[:window_size])
|
|
fft_freqs = np.fft.fftfreq(window_size, 1 / sample_rate)
|
|
|
|
|
|
def band_energy(band, fft_values):
|
|
idx_band = np.where((fft_freqs >= band[0]) & (fft_freqs <= band[1]))[0]
|
|
return np.sum(np.abs(fft_values[idx_band]) ** 2)
|
|
|
|
|
|
energy_low = band_energy(bands["low"], fft_values)
|
|
energy_mid = band_energy(bands["mid"], fft_values)
|
|
energy_high = band_energy(bands["high"], fft_values)
|
|
avg_energy = (energy_low + energy_mid + energy_high) / 3
|
|
|
|
|
|
print(f"low {energy_low:.2e}")
|
|
print(f"mid {energy_mid:.2e}")
|
|
print(f"high {energy_high:.2e}")
|
|
print(f"avg {avg_energy:.2e}")
|
|
|
|
|
|
def adjust(target_energy, current_energy, fft_values, band):
|
|
idx_band = np.where((fft_freqs >= band[0]) & (fft_freqs <= band[1]))[0]
|
|
gain = np.sqrt(target_energy / (current_energy + 1e-6))
|
|
adjusted_fft_values = np.copy(fft_values)
|
|
adjusted_fft_values[idx_band] *= gain
|
|
return adjusted_fft_values
|
|
|
|
|
|
adjusted_low = adjust(avg_energy, energy_low, fft_values, bands["low"])
|
|
adjusted_mid = adjust(avg_energy, energy_mid, fft_values, bands["mid"])
|
|
adjusted_high = adjust(avg_energy, energy_high, fft_values, bands["high"])
|
|
|
|
print(f'adj low {band_energy( bands["low"],adjusted_low):.2e}')
|
|
print(f'adj mid {band_energy(bands["mid"],adjusted_mid):.2e}')
|
|
print(f'adj high {band_energy( bands["high"],adjusted_high):.2e}')
|
|
|
|
adjusted_all = adjusted_low + adjusted_mid + adjusted_high
|
|
full_spectrum = np.concatenate([adjusted_all])
|
|
reconstructed_signal = np.fft.ifft(adjusted_all).real
|
|
reconstructed_signal = np.int16(
|
|
reconstructed_signal / np.max(np.abs(reconstructed_signal)) * np.iinfo(np.int16).max
|
|
)
|
|
|
|
output_file = "adj-" + file
|
|
wav.write(output_file, sample_rate, reconstructed_signal)
|
|
print(f"Adjusted audio written to {output_file}")
|