使用Python中的互相关比较两个音频（.wav）文件

Question

我需要比较两个音频文件以检查它们之间的相似性。因此，我已经使用Python使用了互相关方法。这里是我的代码：

from scipy.io import wavfile
from scipy import signal
import numpy as np


sample_rate_a, data_a = wavfile.read('new.wav')
sample_rate_b, data_b = wavfile.read('result.wav')

data_a = np.float32(data_a)
data_b = np.float32(data_b)
corr = signal.correlate(data_a, data_b)
lags = signal.correlation_lags(len(data_a), len(data_b))
corr = corr / np.max(corr)
def Average(l): 
    avg = sum(l) / len(l) 
    return avg
average = Average(corr) 
  

lag = lags[np.argmax(corr)]
print(corr)
print("Lag =",lag, "np max=", np.max(corr))
print("np.min=",np.min(corr)) 
print("Average of my_list is",abs(average))

我打印了几个值，例如归一化的相关值，滞后和其归一化的最小值和最大值的平均值，以了解我的输出。这是我的输出：

[-3.5679664e-09 -1.1893221e-09  2.3786442e-09 ...  1.1893221e-09
 -1.1893221e-09 -4.7572883e-09]
Lag = 2886023 np max= 1.0
np.min= -1.8993026
Average of my_list is 6.370856069729521e-05

我对此输出有些困惑，因为我无法理解这些值的含义。谁能帮助我弄清楚这些输出值是什么？对于两个音频文件的相似性，我只需要获得一个百分比值。

谢谢

Answer 1

我不知道如何解释您的输出，但是在下面有一个代码，可以使用Python获得两个音频文件的相似性，从而获得100到100的数字，它可以通过从音频文件中生成指纹并使用它们基于它们进行比较。互动相关性

需要 chromaprint 和 ffmpeg 已安装，它也不适用于简短的音频文件，如果这是一个问题，您始终可以降低音频的速度，例如指南请注意，这将增加一点噪音。

# correlation.py
import subprocess
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 = subprocess.getoutput('fpcalc -raw -length %i %s' % (sample_time, filename))
    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(('%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)  

if __name__ == "__main__":    
    correlate(SOURCE_FILE, TARGET_FILE)  

代码从： https：//shivama20505.medium.com/audioum.com/audio-signalals， - 比较-23E431ED2207