What is extracted from speech as a feature of emotion？

[alone-86]

I notice that there is no introduction or description of the features you exttracted from the .wav of
database.
The only description is the code 👍

    if extract_features:
        win_size = 0.04
        step = 0.01
        Fglobal = []
        i = 0
        for (x, Fs) in db.data:
            ############
            F = audioFeatureExtraction.stFeatureExtraction(x, Fs, win_size * Fs, step * Fs)
            Fglobal.append(np.concatenate((np.mean(F[0], axis=1),np.std(F[0], axis=1)))) 
            #############
            ##I think these are all of the code which are used to extract  features


            sys.stdout.write("\033[F")  # cursor up one line
            i = i + 1;
            print "Extracting features " + str(i) + '/' + str(n_samples) + " from data..."

        print "Saving features to file..."
        cPickle.dump(Fglobal, open(db_type + '_features.p', 'wb'))

So, could you give some introdaction to what features you extracted from the file ?
( the mean and standard deviation ？)

Thank you very much, and sorry for my poor english.

[alone-86]

我注意到，没有从
数据库.wav中提取或介绍的功能。
唯一的描述是代码👍

    如果 extract_features：
        win_size =  0.04 
        步=  0.01 
        Fglobal = []
        我=  0 
        为（X，FS）在 db.data：
            ＃ ########### 
            ˚F = audioFeatureExtraction.stFeatureExtraction（X，FS，所以win_size * Fs的步骤* FS）
            Fglobal.append（np.concatenate（（np.mean（F [ 0 ]，轴= 1），np.std（F [ 0 ]，轴= 1）））） 
            ＃ ########## ## 
            ＃＃我觉得这些都被用来提取功能的代码


            sys.stdout.write（“ \ 033 [F ”）   ＃将光标向上移一行 
            i = i +  1 ；
            打印 “提取特征”  +  str（i）+  ' / '  +  str（n_samples）+  “从数据... ”

        打印 “正在将功能保存到文件... ” 
        cPickle.dump（Fglobal，打开（db_type +  ' _features.p '，' wb '））

因此，您可以介绍一下从文件中提取的哪些功能吗？
（平均值和标准偏差？）

非常感谢，对不起，我的英语不好。
I git it
https://github.com/tyiannak/pyAudioAnalysis/wiki/3.-Feature-Extraction