为什么我的代码在计算相关性时会产生值错误？

Question

我正在尝试创建一个脚本来比较两个音频样本并确定它们是否相似（将背景噪声等因素考虑在内将意味着较低的相关性，因此“通过”将根据某些经验法则任意确定）。 我写了一段代码，但我产生了我不知道如何调试的错误。

具体来说，该代码在相关函数中生成以下错误： ValueError: object of too small depth for the desired array 。

我不确定这是否是因为我向函数传递的参数太少，但我真的无法找到问题的根源。 代码出现在下面，应该比较完整。

# compare.py
import argparse

from numpy 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

    SOURCE_FILE = "Comparison1.wav"
    TARGET_FILE = "Comparison2.wav"

    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
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)

Answer 1

您的代码中有一点错误，更具体地说：

SOURCE_FILE = "Comparison1.wav"
TARGET_FILE = "Comparison2.wav"

在这里，您将此变量分配给一个字符串（不是文件）。 从那时起，它们将分别作为“Comparison1.wav”和“Comparison2.wav”字符串进行处理。