compare.py

# compare.py 
import argparse
from correlation import correlate

def initialize():
    parser = argparse.ArgumentParser()
    parser.add_argument("-i ", "--source-file", help="source file")
    parser.add_argument("-o ", "--target-file", help="target file")
    args = parser.parse_args()
  
    SOURCE_FILE = args.source_file if args.source_file else None
    TARGET_FILE = args.target_file if args.target_file else None
    if not SOURCE_FILE or not TARGET_FILE:
      raise Exception("Source or Target files not specified.")
    return SOURCE_FILE, TARGET_FILE
  
if __name__ == "__main__":
    SOURCE_FILE, TARGET_FILE = initialize()
    correlate(SOURCE_FILE, TARGET_FILE)

correlation.py

# correlation.py
import commands 
import numpy 

# seconds to sample audio file for
sample_time = 500
# number of points to scan cross correlation over
span = 150
# step size (in points) of cross correlation
step = 1
# minimum number of points that must overlap in cross correlation
# exception is raised if this cannot be met
min_overlap = 20
# report match when cross correlation has a peak exceeding threshold
threshold = 0.5

# calculate fingerprint
def calculate_fingerprints(filename):
    fpcalc_out = commands.getoutput('fpcalc -raw -length %i %s'
                                    % (sample_time, filename))
    fingerprint_index = fpcalc_out.find('FINGERPRINT=') + 12
    # convert fingerprint to list of integers
    fingerprints = map(int, fpcalc_out[fingerprint_index:].split(','))
    
    return fingerprints
  
# returns correlation between lists
def correlation(listx, listy):
    if len(listx) == 0 or len(listy) == 0:
        # Error checking in main program should prevent us from ever being
        # able to get here.
        raise Exception('Empty lists cannot be correlated.')
    if len(listx) > len(listy):
        listx = listx[:len(listy)]
    elif len(listx) < len(listy):
        listy = listy[:len(listx)]
    
    covariance = 0
    for i in range(len(listx)):
        covariance += 32 - bin(listx[i] ^ listy[i]).count("1")
    covariance = covariance / float(len(listx))
    
    return covariance/32
  
# return cross correlation, with listy offset from listx
def cross_correlation(listx, listy, offset):
    if offset > 0:
        listx = listx[offset:]
        listy = listy[:len(listx)]
    elif offset < 0:
        offset = -offset
        listy = listy[offset:]
        listx = listx[:len(listy)]
    if min(len(listx), len(listy)) < min_overlap:
        # Error checking in main program should prevent us from ever being
        # able to get here.
        return 
    #raise Exception('Overlap too small: %i' % min(len(listx), len(listy)))
    return correlation(listx, listy)
  
# cross correlate listx and listy with offsets from -span to span
def compare(listx, listy, span, step):
    if span > min(len(listx), len(listy)):
        # Error checking in main program should prevent us from ever being
        # able to get here.
        raise Exception('span >= sample size: %i >= %i\n'
                        % (span, min(len(listx), len(listy)))
                        + 'Reduce span, reduce crop or increase sample_time.')
    corr_xy = []
    for offset in numpy.arange(-span, span + 1, step):
        corr_xy.append(cross_correlation(listx, listy, offset))
    return corr_xy
  
# return index of maximum value in list
def max_index(listx):
    max_index = 0
    max_value = listx[0]
    for i, value in enumerate(listx):
        if value > max_value:
            max_value = value
            max_index = i
    return max_index
  
def get_max_corr(corr, source, target):
    max_corr_index = max_index(corr)
    max_corr_offset = -span + max_corr_index * step
    print "max_corr_index = ", max_corr_index, "max_corr_offset = ", max_corr_offset
# report matches
    if corr[max_corr_index] > threshold:
        print('%s and %s match with correlation of %.4f at offset %i'
             % (source, target, corr[max_corr_index], max_corr_offset)) 

def correlate(source, target):
    fingerprint_source = calculate_fingerprints(source)
    fingerprint_target = calculate_fingerprints(target)
    
    corr = compare(fingerprint_source, fingerprint_target, span, step)
    max_corr_offset = get_max_corr(corr, source, target)

It doesn't seems to work I am getting the below error.

invalid literal for int() with base 10: 'command not found'

Doesn't work. Print on line 87 gives syntax error.
Also this doesn't compile in Python 3:
-Commands module is deprecated. Use subprocess module instead.
-Also numpy module must be installed: pip3 install numpy
-ton of list and map errors

Was it originally written for Python 2?
On Python 2 I get:
Traceback (most recent call last):
File "C:\Temp\ffmpeg\bin\compare.py", line 19, in
correlate(SOURCE_FILE, TARGET_FILE)
File "C:\Temp\ffmpeg\bin\correlation.py", line 94, in correlate
fingerprint_source = calculate_fingerprints(source)
File "C:\Temp\ffmpeg\bin\correlation.py", line 23, in calculate_fingerprints
fingerprints = map(int, fpcalc_out[fingerprint_index:].split(','))
ValueError: invalid literal for int() with base 10: 'recognized as an internal or external command'

Got it working with Python 2.7:
-Commands module is deprecated. Use subprocess module instead.
-Also change commands.getoutput to subprocess.check_output

Environment:

• Mac
• python 2.7.10

a.wav           
b.wav           
compare.py      
correlation.py  

compare.py

  1 # compare.py
  2 import argparse
  3 from correlation import correlate
  4
  5 def initialize():
  6     parser = argparse.ArgumentParser()
  7     parser.add_argument("-i ", "--a.wav", help="source file")
  8     parser.add_argument("-o ", "--b.wav", help="target file")
  9     args = parser.parse_args()
 10
 11     SOURCE_FILE = args.source_file if args.source_file else None
 12     TARGET_FILE = args.target_file if args.target_file else None
 13     if not SOURCE_FILE or not TARGET_FILE:
 14       raise Exception("Source or Target files not specified.")
 15     return SOURCE_FILE, TARGET_FILE
 16
 17 if __name__ == "__main__":
 18     SOURCE_FILE, TARGET_FILE = initialize()
 19     correlate(SOURCE_FILE, TARGET_FILE)

Get error:

Traceback (most recent call last):
  File "compare.py", line 18, in <module>
    SOURCE_FILE, TARGET_FILE = initialize()
  File "compare.py", line 11, in initialize
    SOURCE_FILE = args.source_file if args.source_file else None
AttributeError: 'Namespace' object has no attribute 'source_file'

Environment : python 3.8 , windows 10
Got this error for above code

Traceback (most recent call last):
File "compare.py", line 21, in
correlate(SOURCE_FILE, TARGET_FILE)
File "E:\Test_scripts\TTS\correlation.py", line 103, in correlate
corr = compare(fingerprint_source, fingerprint_target, span, step)
File "E:\Test_scripts\TTS\correlation.py", line 66, in compare
if span > min(len(listx), len(listy)):
TypeError: object of type 'map' has no len()

How to run this?

how to run this code in python 3.???

Useful scripts, thanks, here's the ported version https://github.com/kdave/audio-compare .

how I can assign source and target files?