尝试在 Python 中获取 .wav 文件的频率
Trying to get the frequencies of a .wav file in Python
我知道 Python 中关于 .wav 文件的问题几乎被打死了，但我感到非常沮丧，因为似乎没有人的答案对我有用。我想做的事情对我来说似乎相对简单：我想确切地知道在给定时间 .wav 文件中有哪些频率。我想知道，例如 "from the time n milliseconds to n + 10 milliseconds, the average frequency of the sound was x hertz"。我见过人们谈论傅里叶变换和 Goertzel 算法，以及各种模块，我似乎无法弄清楚如何去做我所描述的事情。我已经尝试查找 "find frequency of a wav file in python" 之类的东西大约二十次，但无济于事。有人可以帮我吗？
我正在寻找的是像这个伪代码这样的解决方案，或者至少是一个可以做一些类似于伪代码的事情的解决方案：
import some_module_that_can_help_me_do_this as freq
file = 'output.wav'
start_time = 1000 # Start 1000 milliseconds into the file
end_time = 1010 # End 10 milliseconds thereafter
print("Average frequency = " + str(freq.average(start_time, end_time)) + " hz")
请假设（我相信你能看出来）我是个数学白痴。这是我在这里的第一个问题所以要温和
尝试下面的方法，它对我生成的频率为 1234 的正弦波文件有效
from this page.
from scipy.io import wavfile
def freq(file, start_time, end_time):
sample_rate, data = wavfile.read(file)
start_point = int(sample_rate * start_time / 1000)
end_point = int(sample_rate * end_time / 1000)
length = (end_time - start_time) / 1000
counter = 0
for i in range(start_point, end_point):
if data[i] < 0 and data[i+1] > 0:
counter += 1
return counter/length
freq("sin.wav", 1000 ,2100)
1231.8181818181818
已编辑：稍微清理了循环
如果您想检测 pitch of a sound (and it seems you do), then in terms of Python libraries your best bet is aubio. Please consult this example 以进行实施。
import sys
from aubio import source, pitch
win_s = 4096
hop_s = 512
s = source(your_file, samplerate, hop_s)
samplerate = s.samplerate
tolerance = 0.8
pitch_o = pitch("yin", win_s, hop_s, samplerate)
pitch_o.set_unit("midi")
pitch_o.set_tolerance(tolerance)
pitches = []
confidences = []
total_frames = 0
while True:
samples, read = s()
pitch = pitch_o(samples)[0]
pitches += [pitch]
confidence = pitch_o.get_confidence()
confidences += [confidence]
total_frames += read
if read < hop_s: break
print("Average frequency = " + str(np.array(pitches).mean()) + " hz")
一定要检查docs音调检测方法。
我还认为您可能对在不使用任何特殊库的情况下估算平均频率和其他一些音频参数感兴趣。让我们只使用 numpy 吧！这应该可以让您更好地了解如何计算此类音频功能。它基于 specprop from seewave 包。检查文档以了解计算特征的含义。
import numpy as np
def spectral_properties(y: np.ndarray, fs: int) -> dict:
spec = np.abs(np.fft.rfft(y))
freq = np.fft.rfftfreq(len(y), d=1 / fs)
spec = np.abs(spec)
amp = spec / spec.sum()
mean = (freq * amp).sum()
sd = np.sqrt(np.sum(amp * ((freq - mean) ** 2)))
amp_cumsum = np.cumsum(amp)
median = freq[len(amp_cumsum[amp_cumsum <= 0.5]) + 1]
mode = freq[amp.argmax()]
Q25 = freq[len(amp_cumsum[amp_cumsum <= 0.25]) + 1]
Q75 = freq[len(amp_cumsum[amp_cumsum <= 0.75]) + 1]
IQR = Q75 - Q25
z = amp - amp.mean()
w = amp.std()
skew = ((z ** 3).sum() / (len(spec) - 1)) / w ** 3
kurt = ((z ** 4).sum() / (len(spec) - 1)) / w ** 4
result_d = {
'mean': mean,
'sd': sd,
'median': median,
'mode': mode,
'Q25': Q25,
'Q75': Q75,
'IQR': IQR,
'skew': skew,
'kurt': kurt
}
return result_d
我感到 OP 很沮丧 - 如果有人需要，找到如何获取频谱图的值而不是查看频谱图图像应该不难：
#!/usr/bin/env python
import librosa
import sys
import numpy as np
import matplotlib.pyplot as plt
import librosa.display
np.set_printoptions(threshold=sys.maxsize)
filename = 'filename.wav'
Fs = 44100
clip, sample_rate = librosa.load(filename, sr=Fs)
n_fft = 1024 # frame length
start = 0
hop_length=512
#commented out code to display Spectrogram
X = librosa.stft(clip, n_fft=n_fft, hop_length=hop_length)
#Xdb = librosa.amplitude_to_db(abs(X))
#plt.figure(figsize=(14, 5))
#librosa.display.specshow(Xdb, sr=Fs, x_axis='time', y_axis='hz')
#If to pring log of frequencies
#librosa.display.specshow(Xdb, sr=Fs, x_axis='time', y_axis='log')
#plt.colorbar()
#librosa.display.waveplot(clip, sr=Fs)
#plt.show()
#now print all values
t_samples = np.arange(clip.shape[0]) / Fs
t_frames = np.arange(X.shape[1]) * hop_length / Fs
#f_hertz = np.arange(N / 2 + 1) * Fs / N # Works only when N is even
f_hertz = np.fft.rfftfreq(n_fft, 1 / Fs) # Works also when N is odd
#example
print('Time (seconds) of last sample:', t_samples[-1])
print('Time (seconds) of last frame: ', t_frames[-1])
print('Frequency (Hz) of last bin: ', f_hertz[-1])
print('Time (seconds) :', len(t_samples))
#prints array of time frames
print('Time of frames (seconds) : ', t_frames)
#prints array of frequency bins
print('Frequency (Hz) : ', f_hertz)
print('Number of frames : ', len(t_frames))
print('Number of bins : ', len(f_hertz))
#This code is working to printout frame by frame intensity of each frequency
#on top line gives freq bins
curLine = 'Bins,'
for b in range(1, len(f_hertz)):
curLine += str(f_hertz[b]) + ','
print(curLine)
curLine = ''
for f in range(1, len(t_frames)):
curLine = str(t_frames[f]) + ','
for b in range(1, len(f_hertz)): #for each frame, we get list of bin values printed
curLine += str("%.02f" % np.abs(X[b, f])) + ','
#remove format of the float for full details if needed
#curLine += str(np.abs(X[b, f])) + ','
#print other useful info like phase of frequency bin b at frame f.
#curLine += str("%.02f" % np.angle(X[b, f])) + ','
print(curLine)
这个答案很晚，但你可以试试这个：
（注意：我的大部分功劳都来自其他 SO 帖子和这篇关于使用 Python 的 FFT 的精彩文章：https://realpython.com/python-scipy-fft/）
import numpy as np
from scipy.fft import *
from scipy.io import wavfile
def freq(file, start_time, end_time):
# Open the file and convert to mono
sr, data = wavfile.read(file)
if data.ndim > 1:
data = data[:, 0]
else:
pass
# Return a slice of the data from start_time to end_time
dataToRead = data[int(start_time * sr / 1000) : int(end_time * sr / 1000) + 1]
# Fourier Transform
N = len(dataToRead)
yf = rfft(dataToRead)
xf = rfftfreq(N, 1 / sr)
# Uncomment these to see the frequency spectrum as a plot
# plt.plot(xf, np.abs(yf))
# plt.show()
# Get the most dominant frequency and return it
idx = np.argmax(np.abs(yf))
freq = xf[idx]
return freq
此代码适用于任何 .wav 文件，但可能略有偏差，因为它仅 returns 最主要的频率，而且它仅使用音频的第一个通道 (如果不是单声道）。
如果您想了解有关傅立叶变换工作原理的更多信息，请观看 3blue1brown 提供的带有直观解释的视频：https://www.youtube.com/watch?v=spUNpyF58BY
我知道 Python 中关于 .wav 文件的问题几乎被打死了，但我感到非常沮丧，因为似乎没有人的答案对我有用。我想做的事情对我来说似乎相对简单：我想确切地知道在给定时间 .wav 文件中有哪些频率。我想知道，例如 "from the time n milliseconds to n + 10 milliseconds, the average frequency of the sound was x hertz"。我见过人们谈论傅里叶变换和 Goertzel 算法，以及各种模块，我似乎无法弄清楚如何去做我所描述的事情。我已经尝试查找 "find frequency of a wav file in python" 之类的东西大约二十次，但无济于事。有人可以帮我吗？
我正在寻找的是像这个伪代码这样的解决方案，或者至少是一个可以做一些类似于伪代码的事情的解决方案：
import some_module_that_can_help_me_do_this as freq
file = 'output.wav'
start_time = 1000 # Start 1000 milliseconds into the file
end_time = 1010 # End 10 milliseconds thereafter
print("Average frequency = " + str(freq.average(start_time, end_time)) + " hz")
请假设（我相信你能看出来）我是个数学白痴。这是我在这里的第一个问题所以要温和
尝试下面的方法，它对我生成的频率为 1234 的正弦波文件有效 from this page.
from scipy.io import wavfile
def freq(file, start_time, end_time):
sample_rate, data = wavfile.read(file)
start_point = int(sample_rate * start_time / 1000)
end_point = int(sample_rate * end_time / 1000)
length = (end_time - start_time) / 1000
counter = 0
for i in range(start_point, end_point):
if data[i] < 0 and data[i+1] > 0:
counter += 1
return counter/length
freq("sin.wav", 1000 ,2100)
1231.8181818181818
已编辑：稍微清理了循环
如果您想检测 pitch of a sound (and it seems you do), then in terms of Python libraries your best bet is aubio. Please consult this example 以进行实施。
import sys
from aubio import source, pitch
win_s = 4096
hop_s = 512
s = source(your_file, samplerate, hop_s)
samplerate = s.samplerate
tolerance = 0.8
pitch_o = pitch("yin", win_s, hop_s, samplerate)
pitch_o.set_unit("midi")
pitch_o.set_tolerance(tolerance)
pitches = []
confidences = []
total_frames = 0
while True:
samples, read = s()
pitch = pitch_o(samples)[0]
pitches += [pitch]
confidence = pitch_o.get_confidence()
confidences += [confidence]
total_frames += read
if read < hop_s: break
print("Average frequency = " + str(np.array(pitches).mean()) + " hz")
一定要检查docs音调检测方法。
我还认为您可能对在不使用任何特殊库的情况下估算平均频率和其他一些音频参数感兴趣。让我们只使用 numpy 吧！这应该可以让您更好地了解如何计算此类音频功能。它基于 specprop from seewave 包。检查文档以了解计算特征的含义。
import numpy as np
def spectral_properties(y: np.ndarray, fs: int) -> dict:
spec = np.abs(np.fft.rfft(y))
freq = np.fft.rfftfreq(len(y), d=1 / fs)
spec = np.abs(spec)
amp = spec / spec.sum()
mean = (freq * amp).sum()
sd = np.sqrt(np.sum(amp * ((freq - mean) ** 2)))
amp_cumsum = np.cumsum(amp)
median = freq[len(amp_cumsum[amp_cumsum <= 0.5]) + 1]
mode = freq[amp.argmax()]
Q25 = freq[len(amp_cumsum[amp_cumsum <= 0.25]) + 1]
Q75 = freq[len(amp_cumsum[amp_cumsum <= 0.75]) + 1]
IQR = Q75 - Q25
z = amp - amp.mean()
w = amp.std()
skew = ((z ** 3).sum() / (len(spec) - 1)) / w ** 3
kurt = ((z ** 4).sum() / (len(spec) - 1)) / w ** 4
result_d = {
'mean': mean,
'sd': sd,
'median': median,
'mode': mode,
'Q25': Q25,
'Q75': Q75,
'IQR': IQR,
'skew': skew,
'kurt': kurt
}
return result_d
我感到 OP 很沮丧 - 如果有人需要，找到如何获取频谱图的值而不是查看频谱图图像应该不难：
#!/usr/bin/env python
import librosa
import sys
import numpy as np
import matplotlib.pyplot as plt
import librosa.display
np.set_printoptions(threshold=sys.maxsize)
filename = 'filename.wav'
Fs = 44100
clip, sample_rate = librosa.load(filename, sr=Fs)
n_fft = 1024 # frame length
start = 0
hop_length=512
#commented out code to display Spectrogram
X = librosa.stft(clip, n_fft=n_fft, hop_length=hop_length)
#Xdb = librosa.amplitude_to_db(abs(X))
#plt.figure(figsize=(14, 5))
#librosa.display.specshow(Xdb, sr=Fs, x_axis='time', y_axis='hz')
#If to pring log of frequencies
#librosa.display.specshow(Xdb, sr=Fs, x_axis='time', y_axis='log')
#plt.colorbar()
#librosa.display.waveplot(clip, sr=Fs)
#plt.show()
#now print all values
t_samples = np.arange(clip.shape[0]) / Fs
t_frames = np.arange(X.shape[1]) * hop_length / Fs
#f_hertz = np.arange(N / 2 + 1) * Fs / N # Works only when N is even
f_hertz = np.fft.rfftfreq(n_fft, 1 / Fs) # Works also when N is odd
#example
print('Time (seconds) of last sample:', t_samples[-1])
print('Time (seconds) of last frame: ', t_frames[-1])
print('Frequency (Hz) of last bin: ', f_hertz[-1])
print('Time (seconds) :', len(t_samples))
#prints array of time frames
print('Time of frames (seconds) : ', t_frames)
#prints array of frequency bins
print('Frequency (Hz) : ', f_hertz)
print('Number of frames : ', len(t_frames))
print('Number of bins : ', len(f_hertz))
#This code is working to printout frame by frame intensity of each frequency
#on top line gives freq bins
curLine = 'Bins,'
for b in range(1, len(f_hertz)):
curLine += str(f_hertz[b]) + ','
print(curLine)
curLine = ''
for f in range(1, len(t_frames)):
curLine = str(t_frames[f]) + ','
for b in range(1, len(f_hertz)): #for each frame, we get list of bin values printed
curLine += str("%.02f" % np.abs(X[b, f])) + ','
#remove format of the float for full details if needed
#curLine += str(np.abs(X[b, f])) + ','
#print other useful info like phase of frequency bin b at frame f.
#curLine += str("%.02f" % np.angle(X[b, f])) + ','
print(curLine)
这个答案很晚，但你可以试试这个：
（注意：我的大部分功劳都来自其他 SO 帖子和这篇关于使用 Python 的 FFT 的精彩文章：https://realpython.com/python-scipy-fft/）
import numpy as np
from scipy.fft import *
from scipy.io import wavfile
def freq(file, start_time, end_time):
# Open the file and convert to mono
sr, data = wavfile.read(file)
if data.ndim > 1:
data = data[:, 0]
else:
pass
# Return a slice of the data from start_time to end_time
dataToRead = data[int(start_time * sr / 1000) : int(end_time * sr / 1000) + 1]
# Fourier Transform
N = len(dataToRead)
yf = rfft(dataToRead)
xf = rfftfreq(N, 1 / sr)
# Uncomment these to see the frequency spectrum as a plot
# plt.plot(xf, np.abs(yf))
# plt.show()
# Get the most dominant frequency and return it
idx = np.argmax(np.abs(yf))
freq = xf[idx]
return freq
此代码适用于任何 .wav 文件，但可能略有偏差，因为它仅 returns 最主要的频率，而且它仅使用音频的第一个通道 (如果不是单声道）。
如果您想了解有关傅立叶变换工作原理的更多信息，请观看 3blue1brown 提供的带有直观解释的视频：https://www.youtube.com/watch?v=spUNpyF58BY