Trying to get the frequencies of a .wav file in Python

Question

What I'm trying to do seems simple: I want to know exactly what frequencies there are in a .wav file at given times; i.e. "from the time n milliseconds to n + 10 milliseconds, the average frequency of the sound was x hertz". I have seen people talking about Fourier transforms and Goertzel algorithms, as well as various modules, that I can't seem to figure out how to get to do what I've described.

What I'm looking for is a solution like this pseudocode, or at least one that will do something like what the pseudocode is getting at:

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")

I don't come from a mathematics background, so I don't want to have to understand the implementation details.

Answer 1

This answer is quite late, but you could try this:

(Note: I deserve very little credit for this since I got most of it from other SO posts and this great article on FFT using Python: 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

This code can work for any .wav file, but it may be slightly off since it only returns the most dominant frequency, and also because it only uses the first channel of the audio (if not mono).

If you want to learn more about how the Fourier transform works, check out this video by 3blue1brown with a visual explanation: https://www.youtube.com/watch?v=spUNpyF58BY

Answer 2

I felt the OPs frustration - it shouldnt be so hard to find how to get values of the sprectrogram instead of seeing the spectrogram image if someone needs to:

#!/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)

Answer 3

If you'd like to detect pitch of a sound (and it seems you do), then in terms of Python libraries your best bet is aubio. Please consult this example for implementation.

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")

Be sure to check docs on pitch detection methods.

I also thought you might be interested in estimation of mean frequency and some other audio parameters without using any special libraries. Let's just use numpy! This should give you much better insight into how such audio features can be calculated. It's based off specprop from seewave package. Check docs for meaning of computed features.

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

Answer 4

Try something along the below, it worked for me with a sine wave file with a freq of 1234 I generated 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

edited: cleaned up for loop a bit