marioruggieri / emotion-recognition-from-speech Goto Github PK

I get this error message in extract_fearures

I am getting an error that DATASET IS NOT REGISTERED. PLEASE CREATE A METHOD TO READ IT

I am a new guy just study to learn speech emotion recognition.
Could someone tell me how to load berlin database,such as where to add my berlin_database's path.

Loading data from berlin dataset...
Error in readAudioFile(): Unknown file type!
Traceback (most recent call last):
File "emorecognition.py", line 41, in
db = Dataset(path,db_type,decode=False)
File "/home/zzl/Emotion-Recognition-from-Speech/src/dataset.py", line 18, in init
self.get_berlin_dataset(path)
File "/home/zzl/Emotion-Recognition-from-Speech/src/dataset.py", line 35, in get_berlin_dataset
self.targets.append(classes[audio[5]])
IndexError: string index out of range

Hello Sir,
Greetings!!
I am not clear about the usage of your code of "Emotion recognition from speech". I am facing problem for interpretation of the exact meaning of the arguments to be passed for -l and -e and what values we need to pass.
So, please help us out we would be very grateful to make it happen using your repository.
Hoping for the positive response
Thanking you
Prasad Parsodkar

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.