添加音频相似度检测

aiDogProject_docker/aiDogProject/aiDogApp/Simulate_Calc/main.py

@@ -0,0 +1,22 @@
+from wave_compare import extract_mfcc, compute_similarity
+from datetime import datetime
+# import pickle
+
+# 按间距中的绿色按钮以运行脚本。
+if __name__ == '__main__':
+    # print_hi('Program Start')
+    print("start time:" + str(datetime.now()))
+    sound_wave_1 = "D://Users//Jees//Documents//coding//PuppyVoiceProcessing//wave_files//puppy4a.wav"
+    sound_wave_2 = "D://Users//Jees//Documents//coding//PuppyVoiceProcessing//wave_files//puppy1b.wav"
+
+    mfcc_1 = extract_mfcc(sound_wave_1)
+    mfcc_2 = extract_mfcc(sound_wave_2)
+
+    # 一下两行代码展示将mfcc数据dump成二进制，用于保存在数据库。需要同时import pickle
+    # a = pickle.dumps(mfcc_1)
+    # b = pickle.loads(a)
+
+    similarity = compute_similarity(mfcc_2, mfcc_1)
+    print('similarity result:' + str(similarity))
+    print("end time:" + str(datetime.now()))
+

aiDogProject_docker/aiDogProject/aiDogApp/Simulate_Calc/wave_compare.py

@@ -0,0 +1,33 @@
+from datetime import datetime
+import librosa
+# from matplotlib import pyplot
+from librosa.feature import mfcc
+import numpy as np
+from scipy.spatial.distance import euclidean
+
+
+def extract_mfcc(filename, num_mfcc=13):
+    # 取低频维度上的部分值输出，语音能量大多集中在低频域，数值一般取13。
+    print("start extract_mfcc time:" + filename + str(datetime.now()))
+    audio, sample_rate = librosa.load(filename)
+    # pyplot.figure(figsize=(14, 5))
+    # librosa.display.waveshow(y=audio, sr=sample_rate)
+    # pyplot.title('Wave Form of ' + filename)
+    # pyplot.show()
+    mfcc_result = mfcc(y=audio, sr=sample_rate, n_mfcc=num_mfcc)
+    mean_mfcc = np.mean(mfcc_result, axis=1)
+    print("end extract_mfcc time:" + filename + str(datetime.now()))
+    return mean_mfcc
+
+
+def compute_similarity(feature_1, feature_2):
+    print("start compute_similarity time:" + str(datetime.now()))
+    distance = euclidean(feature_1, feature_2)
+    result = (100-distance)/100
+    # 以下2种弃用的计算方式
+    # result = 1-(distance*distance / 10000)
+    # result = 1 - np.square((100-distance)/100)
+    if result < 0:
+        result = 0
+    print("end compute_similarity time:" + str(datetime.now()))
+    return result