您好，我正在尝试使用python做口音分类器 我首先需要过滤和分离声音中的噪音，我在下面做了分离
from __future__ import print_function
import numpy as np
import matplotlib.pyplot as plt
import librosa
import librosa.display
y, sr = librosa.load('/home/osboxes/Desktop/AccentReco1/audio-files/egyptiansong.mp3', duration=124)
# And compute the spectrogram magnitude and phase
S_full, phase = librosa.magphase(librosa.stft(y))
#Plot a 5-second slice of the spectrum
idx = slice(*librosa.time_to_frames([30, 35], sr=sr))
plt.figure(figsize=(12, 4))
librosa.display.specshow(librosa.amplitude_to_db(S_full[:, idx], ref=np.max),
y_axis='log', x_axis='time', sr=sr)
plt.colorbar()
plt.tight_layout()
# We'll compare frames using cosine similarity, and aggregate similar frames
# by taking their (per-frequency) median value.
#
# To avoid being biased by local continuity, we constrain similar frames to be
# separated by at least 2 seconds.
#
# This suppresses sparse/non-repetetitive deviations from the average spectrum,
# and works well to discard vocal elements.
S_filter = librosa.decompose.nn_filter(S_full,
aggregate=np.median,
metric='cosine',
width=int(librosa.time_to_frames(2, sr=sr)))
# The output of the filter shouldn't be greater than the input
# if we assume signals are additive. Taking the pointwise minimium
# with the input spectrum forces this.
S_filter = np.minimum(S_full, S_filter)
# We can also use a margin to reduce bleed between the vocals and instrumentation masks.
# Note: the margins need not be equal for foreground and background separation
margin_i, margin_v = 2, 10
power = 2
mask_i = librosa.util.softmask(S_filter,
margin_i * (S_full - S_filter),
power=power)
mask_v = librosa.util.softmask(S_full - S_filter,
margin_v * S_filter,
power=power)
# Once we have the masks, simply multiply them with the input spectrum
# to separate the components
S_foreground = mask_v * S_full
S_background = mask_i * S_full
print(S_foreground)
如何获取分离的前景并将其转换为wav文件，以便进入下一阶段，即特征提取（MFCC提取）