计算 python 中 .wav 文件的频谱图
Calculating spectrogram of .wav files in python
我正在尝试使用 Python 从 .wav 个文件中计算频谱图。为了做到这一点，我按照可以找到的说明进行操作 in here。我首先使用 librosa 库读取 .wav 个文件。 link 中的代码可以正常工作。该代码是：
sig, rate = librosa.load(file, sr = None)
sig = buf_to_int(sig, n_bytes=2)
spectrogram = sig2spec(rate, sig)
和函数 sig2spec:
def sig2spec(signal, sample_rate):
# Read the file.
# sample_rate, signal = scipy.io.wavfile.read(filename)
# signal = signal[0:int(1.5 * sample_rate)] # Keep the first 3.5 seconds
# plt.plot(signal)
# plt.show()
# Pre-emphasis step: Amplification of the high frequencies (HF)
# (1) balance the frequency spectrum since HF usually have smaller magnitudes compared to LF
# (2) avoid numerical problems during the Fourier transform operation and
# (3) may also improve the Signal-to-Noise Ratio (SNR).
pre_emphasis = 0.97
emphasized_signal = numpy.append(signal[0], signal[1:] - pre_emphasis * signal[:-1])
# plt.plot(emphasized_signal)
# plt.show()
# Consequently, we split the signal into short time windows. We can safely make the assumption that
# an audio signal is stationary over a small short period of time. Those windows size are balanced from the
# parameter called frame_size, while the overlap between consecutive windows is controlled from the
# variable frame_stride.
frame_size = 0.025
frame_stride = 0.01
frame_length, frame_step = frame_size * sample_rate, frame_stride * sample_rate # Convert from seconds to samples
signal_length = len(emphasized_signal)
frame_length = int(round(frame_length))
frame_step = int(round(frame_step))
num_frames = int(numpy.ceil(float(numpy.abs(signal_length - frame_length)) / frame_step))
# Make sure that we have at least 1 frame
pad_signal_length = num_frames * frame_step + frame_length
z = numpy.zeros((pad_signal_length - signal_length))
pad_signal = numpy.append(emphasized_signal, z)
# Pad Signal to make sure that all frames have equal
# number of samples without truncating any samples from the original signal
indices = numpy.tile(numpy.arange(0, frame_length), (num_frames, 1)) \
+ numpy.tile(numpy.arange(0, num_frames * frame_step, frame_step), (frame_length, 1)).T
frames = pad_signal[indices.astype(numpy.int32, copy=False)]
# Apply hamming windows. The rationale behind that is the assumption made by the FFT that the data
# is infinite and to reduce spectral leakage.
frames *= numpy.hamming(frame_length)
# Fourier-Transform and Power Spectrum
nfft = 2048
mag_frames = numpy.absolute(numpy.fft.rfft(frames, nfft)) # Magnitude of the FFT
pow_frames = ((1.0 / nfft) * (mag_frames ** 2)) # Power Spectrum
# Transform the FFT to MEL scale
nfilt = 40
low_freq_mel = 0
high_freq_mel = (2595 * numpy.log10(1 + (sample_rate / 2) / 700)) # Convert Hz to Mel
mel_points = numpy.linspace(low_freq_mel, high_freq_mel, nfilt + 2) # Equally spaced in Mel scale
hz_points = (700 * (10 ** (mel_points / 2595) - 1)) # Convert Mel to Hz
bin = numpy.floor((nfft + 1) * hz_points / sample_rate)
fbank = numpy.zeros((nfilt, int(numpy.floor(nfft / 2 + 1))))
for m in range(1, nfilt + 1):
f_m_minus = int(bin[m - 1]) # left
f_m = int(bin[m]) # center
f_m_plus = int(bin[m + 1]) # right
for k in range(f_m_minus, f_m):
fbank[m - 1, k] = (k - bin[m - 1]) / (bin[m] - bin[m - 1])
for k in range(f_m, f_m_plus):
fbank[m - 1, k] = (bin[m + 1] - k) / (bin[m + 1] - bin[m])
filter_banks = numpy.dot(pow_frames, fbank.T)
filter_banks = numpy.where(filter_banks == 0, numpy.finfo(float).eps, filter_banks) # Numerical Stability
filter_banks = 20 * numpy.log10(filter_banks) # dB
return (filter_banks/ np.amax(filter_banks))*255
我可以生成如下所示的图像：
但是，在某些情况下，我的频谱图如下所示：
发生了一些非常奇怪的事情，因为在信号开始时，图像中有一些蓝色条纹，我不明白它们是否真的意味着什么，或者在计算频谱图时出现错误。我想这个问题与规范化有关，但我不确定到底是什么。
编辑： 我尝试使用库中推荐的 librosa：
sig, rate = librosa.load("audio.wav", sr = None)
spectrogram = librosa.feature.melspectrogram(y=sig, sr=rate)
spec_shape = spectrogram.shape
fig = plt.figure(figsize=(spec_shape), dpi=5)
lidis.specshow(spectrogram.T, cmap=cm.jet)
plt.tight_layout()
plt.savefig("spec.jpg")
现在的规格几乎到处都是深蓝色:
可能是因为您没有调整 librosa melspectrogram 方法的参数。
在您最初的实现中，您指定了 nfft=2048。这可以传递给 melspectrogram，你会看到不同的结果。
本文介绍了'waveform frequency resolution'和'fft resolution'，它们是做FT时的重要参数。了解它们可能有助于再现您的原始频谱图。
http://www.bitweenie.com/listings/fft-zero-padding/
specshow 方法也有各种参数，这些参数将直接影响您正在制作的图。
此堆栈帖子列出了 MATLAB 中的各种频谱图参数，但您可以得出 MATLAB 版本和 librosa 版本之间的相似之处。
我正在尝试使用 Python 从 .wav 个文件中计算频谱图。为了做到这一点，我按照可以找到的说明进行操作 in here。我首先使用 librosa 库读取 .wav 个文件。 link 中的代码可以正常工作。该代码是：
sig, rate = librosa.load(file, sr = None)
sig = buf_to_int(sig, n_bytes=2)
spectrogram = sig2spec(rate, sig)
和函数 sig2spec:
def sig2spec(signal, sample_rate):
# Read the file.
# sample_rate, signal = scipy.io.wavfile.read(filename)
# signal = signal[0:int(1.5 * sample_rate)] # Keep the first 3.5 seconds
# plt.plot(signal)
# plt.show()
# Pre-emphasis step: Amplification of the high frequencies (HF)
# (1) balance the frequency spectrum since HF usually have smaller magnitudes compared to LF
# (2) avoid numerical problems during the Fourier transform operation and
# (3) may also improve the Signal-to-Noise Ratio (SNR).
pre_emphasis = 0.97
emphasized_signal = numpy.append(signal[0], signal[1:] - pre_emphasis * signal[:-1])
# plt.plot(emphasized_signal)
# plt.show()
# Consequently, we split the signal into short time windows. We can safely make the assumption that
# an audio signal is stationary over a small short period of time. Those windows size are balanced from the
# parameter called frame_size, while the overlap between consecutive windows is controlled from the
# variable frame_stride.
frame_size = 0.025
frame_stride = 0.01
frame_length, frame_step = frame_size * sample_rate, frame_stride * sample_rate # Convert from seconds to samples
signal_length = len(emphasized_signal)
frame_length = int(round(frame_length))
frame_step = int(round(frame_step))
num_frames = int(numpy.ceil(float(numpy.abs(signal_length - frame_length)) / frame_step))
# Make sure that we have at least 1 frame
pad_signal_length = num_frames * frame_step + frame_length
z = numpy.zeros((pad_signal_length - signal_length))
pad_signal = numpy.append(emphasized_signal, z)
# Pad Signal to make sure that all frames have equal
# number of samples without truncating any samples from the original signal
indices = numpy.tile(numpy.arange(0, frame_length), (num_frames, 1)) \
+ numpy.tile(numpy.arange(0, num_frames * frame_step, frame_step), (frame_length, 1)).T
frames = pad_signal[indices.astype(numpy.int32, copy=False)]
# Apply hamming windows. The rationale behind that is the assumption made by the FFT that the data
# is infinite and to reduce spectral leakage.
frames *= numpy.hamming(frame_length)
# Fourier-Transform and Power Spectrum
nfft = 2048
mag_frames = numpy.absolute(numpy.fft.rfft(frames, nfft)) # Magnitude of the FFT
pow_frames = ((1.0 / nfft) * (mag_frames ** 2)) # Power Spectrum
# Transform the FFT to MEL scale
nfilt = 40
low_freq_mel = 0
high_freq_mel = (2595 * numpy.log10(1 + (sample_rate / 2) / 700)) # Convert Hz to Mel
mel_points = numpy.linspace(low_freq_mel, high_freq_mel, nfilt + 2) # Equally spaced in Mel scale
hz_points = (700 * (10 ** (mel_points / 2595) - 1)) # Convert Mel to Hz
bin = numpy.floor((nfft + 1) * hz_points / sample_rate)
fbank = numpy.zeros((nfilt, int(numpy.floor(nfft / 2 + 1))))
for m in range(1, nfilt + 1):
f_m_minus = int(bin[m - 1]) # left
f_m = int(bin[m]) # center
f_m_plus = int(bin[m + 1]) # right
for k in range(f_m_minus, f_m):
fbank[m - 1, k] = (k - bin[m - 1]) / (bin[m] - bin[m - 1])
for k in range(f_m, f_m_plus):
fbank[m - 1, k] = (bin[m + 1] - k) / (bin[m + 1] - bin[m])
filter_banks = numpy.dot(pow_frames, fbank.T)
filter_banks = numpy.where(filter_banks == 0, numpy.finfo(float).eps, filter_banks) # Numerical Stability
filter_banks = 20 * numpy.log10(filter_banks) # dB
return (filter_banks/ np.amax(filter_banks))*255
我可以生成如下所示的图像：
但是，在某些情况下，我的频谱图如下所示：
发生了一些非常奇怪的事情，因为在信号开始时，图像中有一些蓝色条纹，我不明白它们是否真的意味着什么，或者在计算频谱图时出现错误。我想这个问题与规范化有关，但我不确定到底是什么。
编辑： 我尝试使用库中推荐的 librosa：
sig, rate = librosa.load("audio.wav", sr = None)
spectrogram = librosa.feature.melspectrogram(y=sig, sr=rate)
spec_shape = spectrogram.shape
fig = plt.figure(figsize=(spec_shape), dpi=5)
lidis.specshow(spectrogram.T, cmap=cm.jet)
plt.tight_layout()
plt.savefig("spec.jpg")
现在的规格几乎到处都是深蓝色:
可能是因为您没有调整 librosa melspectrogram 方法的参数。
在您最初的实现中，您指定了 nfft=2048。这可以传递给 melspectrogram，你会看到不同的结果。
本文介绍了'waveform frequency resolution'和'fft resolution'，它们是做FT时的重要参数。了解它们可能有助于再现您的原始频谱图。
http://www.bitweenie.com/listings/fft-zero-padding/
specshow 方法也有各种参数，这些参数将直接影响您正在制作的图。
此堆栈帖子列出了 MATLAB 中的各种频谱图参数，但您可以得出 MATLAB 版本和 librosa 版本之间的相似之处。