Python实现WAV音频分析与线性回归建模

from scipy.io import wavfile
sample_rate, audio_data = wavfile.read("sound/cat/1-47819-C-5.wav")

# 立体声分离
left_channel = audio_data[:, 0]
right_channel = audio_data[:, 1]

# 标准化（均值归零、方差归一）
left_norm = (left_channel - np.mean(left_channel)) / np.std(left_channel)
right_norm = (right_channel - np.mean(right_channel)) / np.std(right_channel)

def linear_regression(x, y):
    n = len(x)
    sum_x, sum_y = np.sum(x), np.sum(y)
    sum_xy = np.sum(x * y)
    sum_x2 = np.sum(x ** 2)
    slope = (n * sum_xy - sum_x * sum_y) / (n * sum_x2 - sum_x ** 2)
    intercept = (sum_y - slope * sum_x) / n
    return slope, intercept

sim_list = []
for i in range(0, len(left_norm)-800, 800):
    x = left_norm[i:i+800:2]  # 左声道隔点采样
    y = right_norm[i:i+800:1] # 右声道连续采样
    slope, intercept = linear_regression(x, y)
    y_pred = slope * x + intercept
    sim = cosine_similarity(y_pred, y)  # 余弦相似度评估拟合效果
    sim_list.append(sim)

def calculate_fit_error(y_true, y_pred):
    mse = np.mean((y_true - y_pred) ** 2)       # 均方误差
    rmse = np.sqrt(mse)                         # 均方根误差
    mae = np.mean(np.abs(y_true - y_pred))      # 平均绝对误差
    return mse, rmse, mae

plt.figure(figsize=(12, 4))
plt.plot(sim_list, marker='o', linestyle='-', color='#FF7043')
plt.title("双声道线性拟合相似度变化趋势", fontsize=14)
plt.xlabel("时间窗口索引", fontsize=12)
plt.ylabel("余弦相似度", fontsize=12)
plt.grid(alpha=0.3)
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from scipy.io import wavfile

# 中文显示支持
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
plt.rcParams['axes.unicode_minus'] = False

def cosine_similarity(a, b):
    """计算余弦相似度"""
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

def linear_regression(x, y):
    """最小二乘法线性回归"""
    n = len(x)
    sum_x, sum_y = np.sum(x), np.sum(y)
    sum_xy = np.sum(x * y)
    sum_x2 = np.sum(x ** 2)
    slope = (n * sum_xy - sum_x * sum_y) / (n * sum_x2 - sum_x ** 2)
    intercept = (sum_y - slope * sum_x) / n
    return slope, intercept

def main():
    # 数据读取
    _, audio = wavfile.read("sound/cat/1-47819-C-5.wav")
    left = (audio[:,0]-np.mean(audio[:,0]))/np.std(audio[:,0])
    right = (audio[:,1]-np.mean(audio[:,1]))/np.std(audio[:,1])
    
    # 滑动窗口分析
    sim_list = []
    for i in range(0, len(left)-800, 800):
        x, y = left[i:i+800:2], right[i:i+800:1]
        if len(x) > len(y): x = x[:len(y)]
        slope, intercept = linear_regression(x, y)
        sim_list.append(cosine_similarity(slope*x+intercept, y))
    
    # 可视化
    plt.plot(sim_list)
    plt.show()

if __name__ == "__main__":
    main()