Invertible STFT and ISTFT in Python

Question

Is there any general-purpose form of short-time Fourier transform with corresponding inverse transform built into SciPy or NumPy or whatever?

There\'s the pyplot

Answer 1

Neither of the above answers worked well OOTB for me. So I modified Steve Tjoa's.

import scipy, pylab
import numpy as np

def stft(x, fs, framesz, hop):
    """
     x - signal
     fs - sample rate
     framesz - frame size
     hop - hop size (frame size = overlap + hop size)
    """
    framesamp = int(framesz*fs)
    hopsamp = int(hop*fs)
    w = scipy.hamming(framesamp)
    X = scipy.array([scipy.fft(w*x[i:i+framesamp]) 
                     for i in range(0, len(x)-framesamp, hopsamp)])
    return X

def istft(X, fs, T, hop):
    """ T - signal length """
    length = T*fs
    x = scipy.zeros(T*fs)
    framesamp = X.shape[1]
    hopsamp = int(hop*fs)
    for n,i in enumerate(range(0, len(x)-framesamp, hopsamp)):
        x[i:i+framesamp] += scipy.real(scipy.ifft(X[n]))
    # calculate the inverse envelope to scale results at the ends.
    env = scipy.zeros(T*fs)
    w = scipy.hamming(framesamp)
    for i in range(0, len(x)-framesamp, hopsamp):
        env[i:i+framesamp] += w
    env[-(length%hopsamp):] += w[-(length%hopsamp):]
    env = np.maximum(env, .01)
    return x/env # right side is still a little messed up...

Answer 2

Found another STFT, but no corresponding inverse function:

http://code.google.com/p/pytfd/source/browse/trunk/pytfd/stft.py

def stft(x, w, L=None):
    ...
    return X_stft

• w is a window function as an array
• L is the overlap, in samples

Answer 3

A fixed version of basj's answer.

import scipy, numpy as np
import matplotlib.pyplot as plt

def stft(x, fftsize=1024, overlap=4):
    hop=fftsize//overlap
    w = scipy.hanning(fftsize+1)[:-1]      # better reconstruction with this trick +1)[:-1]  
    return np.vstack([np.fft.rfft(w*x[i:i+fftsize]) for i in range(0, len(x)-fftsize, hop)])

def istft(X, overlap=4):   
    fftsize=(X.shape[1]-1)*2
    hop=fftsize//overlap
    w=scipy.hanning(fftsize+1)[:-1]
    rcs=int(np.ceil(float(X.shape[0])/float(overlap)))*fftsize
    print(rcs)
    x=np.zeros(rcs)
    wsum=np.zeros(rcs)
    for n,i in zip(X,range(0,len(X)*hop,hop)): 
        l=len(x[i:i+fftsize])
        x[i:i+fftsize] += np.fft.irfft(n).real[:l]   # overlap-add
        wsum[i:i+fftsize] += w[:l]
    pos = wsum != 0
    x[pos] /= wsum[pos]
    return x

a=np.random.random((65536))
b=istft(stft(a))
plt.plot(range(len(a)),a,range(len(b)),b)
plt.show()

Answer 4

If you have access to a C binary library that does what you want, then use http://code.google.com/p/ctypesgen/ to generate a Python interface to that library.

Answer 5

I think scipy.signal has what you are looking for. It has reasonable defaults, supports multiple window types, etc...

http://docs.scipy.org/doc/scipy-0.17.0/reference/generated/scipy.signal.spectrogram.html

from scipy.signal import spectrogram
freq, time, Spec = spectrogram(signal)

Answer 6

I also found this on GitHub, but it seems to operate on pipelines instead of normal arrays:

http://github.com/ronw/frontend/blob/master/basic.py#LID281

def STFT(nfft, nwin=None, nhop=None, winfun=np.hanning):
    ...
    return dataprocessor.Pipeline(Framer(nwin, nhop), Window(winfun),
                                  RFFT(nfft))


def ISTFT(nfft, nwin=None, nhop=None, winfun=np.hanning):
    ...
    return dataprocessor.Pipeline(IRFFT(nfft), Window(winfun),
                                  OverlapAdd(nwin, nhop))