TIMIT_utils.py 文件源码

def get_data(rootdir = TIMIT_main_dir): 
    inputs = []
    targets = []
    for dir_path, sub_dirs, files in os.walk(rootdir):
        for file in files:          
            if (os.path.join(dir_path, file)).endswith('.wav'):
                wav_file_name = os.path.join(dir_path, file)
                input_data, f_s = sf.read(wav_file_name)
                # mfcc_feat = MFCC_input(mfcc(input_data,f_s))
                mfcc_feat = mfcc(input_data,f_s)
                #Delta features
                delta_feat = mfcc_feat[:-1]-mfcc_feat[1:]
                #Delta-Delta features
                deltadelta_feat = delta_feat[:-1]-delta_feat[1:]

                #Removing the first two frames
                mfcc_feat = mfcc_feat[2:]
                delta_feat = delta_feat[1:]

                #Concatenating mfcc, delta and delta-delta features
                full_input = np.concatenate((mfcc_feat,delta_feat,deltadelta_feat), axis=1)

                inputs.append(np.asarray(full_input, dtype=theano.config.floatX))#Rakeshvar wants one frame along each column but i am using Lasagne

                text_file_name = wav_file_name[:-4] + '.txt'
                target_data_file = open(text_file_name)
                target_data = str(target_data_file.read()).lower().translate(None, '!:,".;?')
                # target_data = str(target_data_file.read()).lower().translate(str.maketrans('','', '!:,".;?'))
                target_data = target_data[8:-1]#No '.' in lexfree dictionary
                targets.append(target_data)
    return inputs, targets