属性错误(Python PNCC使用Spafe)模块'scipy‘没有属性'fftpack’

Question

我正在尝试使用这里提供的Spafe项目提取语音特征

https://github.com/SuperKogito/spafe/blob/master/examples/features_pncc_example.ipynb。

我使用了spafe项目中提供的PNCC特征提取程序。

我得到了下面的错误。请帮帮忙。

pnccs = scipy.fftpack.dct(V):，:num_ceps AttributeError:模块'scipy‘没有属性'fftpack’

代码如下所示。

import scipy
from spafe.utils import vis
from spafe.features.pncc import pncc
import scipy.io.wavfile as wav

# init input vars
num_ceps = 13
low_freq = 0
high_freq = 2000
nfilts = 24
nfft = 512
dct_type = 2,
use_energy = False,
lifter = 5
normalize = True

# read wav
(fs, sig) = wav.read("sample.wav")

# compute features
pnccs = pncc(sig=sig,
             fs=fs,
             num_ceps=num_ceps,
             nfilts=nfilts,
             nfft=nfft,
             low_freq=low_freq,
             high_freq=high_freq,
             dct_type=dct_type,
             use_energy=use_energy,
             lifter=lifter,
             normalize=normalize)

# visualize spectogram
vis.spectogram(sig, fs)
# visualize features
vis.visualize_features(pnccs, 'PNCC Index', 'Frame Index')

Answer 1

我觉得你应该避开scipy.fftpack。

传统离散傅立叶变换(scipy.fftpack)

警告:此子模块现在被视为遗留模块，新代码应使用scipy.fft。

https://docs.scipy.org/doc/scipy/reference/fftpack.html