Initial import

README.md

@@ -0,0 +1,58 @@
+# Simple tool to compare audio files
+
+NOTE: I haven't written this, merely found it on the internet and ported to
+python 3.
+
+* https://shivama205.medium.com/audio-signals-comparison-23e431ed2207 "Audio signals: Comparison"
+* https://gist.github.com/shivama205/5578f999a9c88112f5d042ebb83e54d5 scripts from the article
+
+Related projects:
+
+* https://acoustid.org/chromaprint fpcalc
+* numpy
+
+Usage:
+
+Sample files captured from a streaming source without exact start, duration but
+are the same song:
+
+    $ ./compare.py -i file1.mp3 -o file2.mp3
+    Calculating fingerprint by fpcalc for file1.mp3
+    Calculating fingerprint by fpcalc for file2.mp3
+    File A: file1.mp3
+    File B: file2.mp3
+    Match with correlation of 63.74% at offset 55
+
+    $ ./compare.py -i file2.mp3 -o file1.mp3
+    Calculating fingerprint by fpcalc for file2.mp3
+    Calculating fingerprint by fpcalc for file1.mp3
+    File A: file2.mp3
+    File B: file2.mp3
+    Match with correlation of 63.74% at offset -5
+
+For some files the swapped order may not lead to the same results due to offset
+or the way the `fpcalc` fingerprint is generated (see help).
+
+    $ ./compare.py -i file2.mp3 -o file3.mp3
+    Calculating fingerprint by fpcalc for file2.mp3
+    Calculating fingerprint by fpcalc for file3.mp3
+    File A: file2.mp3
+    File B: file3.mp3
+    Match with correlation of 93.01% at offset -24
+
+    $ ./compare.py
+    Calculating fingerprint by fpcalc for file1.mp3
+    Calculating fingerprint by fpcalc for file3.mp3
+    File A: file1.mp3
+    File B: file3.mp3
+    Match with correlation of 63.96% at offset 31
+
+Internally the fingerprint is generated by `fpcalc -length 500`, cached
+versions can be produced by `fpcalc-gen`.
+
+Changes:
+
+- port to python3
+- print the similary as percents
+- print input files on separate lines
+- support precalculated fingerprint in `file.mp3.fpcalc`

compare.py

@@ -0,0 +1,20 @@
+#!/usr/bin/python3
+# 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

@@ -0,0 +1,111 @@
+#!/usr/bin/python3
+
+# correlation.py
+import subprocess
+import numpy
+import os
+
+# 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
+# Generate file.mp3.fpcalc by "fpcalc -raw -length 500 file.mp3"
+def calculate_fingerprints(filename):
+    if os.path.exists(filename + '.fpcalc'):
+        print("Found precalculated fingerprint for %s" % (filename))
+        f = open(filename + '.fpcalc', "r")
+        fpcalc_out = ''.join(f.readlines())
+        f.close()
+    else:
+        print("Calculating fingerprint by fpcalc for %s" % (filename))
+        fpcalc_out = str(subprocess.check_output(['fpcalc', '-raw', '-length', str(sample_time), filename])).strip().replace('\\n', '').replace("'", "")
+
+    fingerprint_index = fpcalc_out.find('FINGERPRINT=') + 12
+    # convert fingerprint to list of integers
+    fingerprints = list(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("File A: %s" % (source))
+        print("File B: %s" % (target))
+        print('Match with correlation of %.2f%% at offset %i'
+             % (corr[max_corr_index] * 100.0, 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)

fpcalc-gen

@@ -0,0 +1,2 @@
+#!/bin/sh
+fpcalc -raw -length 500 "$1" > "$1".fpcalc