语音情感识别、Google Colab、Python

Question

我正在做语音情感识别方面的大学项目，我正在尝试运行这 3 个代码块，但我收到一长串错误，请帮助我

这里是 google colab 的链接 https://colab.research.google.com/drive/1yHyLBbwVhsqiF8bUvd7_7YFDvOhaqzgz#scrollTo=UVbUUU2ueuYC

def extract_feature(file_name, mfcc, chroma, mel):
    with soundfile.SoundFile(file_name) as sound_file:
        X = sound_file.read(dtype="float32")
        sample_rate=sound_file.samplerate
        if chroma:
            stft=np.abs(librosa.stft(X))
        result=np.array([])
        if mfcc:
            mfccs=np.mean(librosa.feature.mfcc(y=X, sr=sample_rate, n_mfcc=40).T, axis=0)
            result=np.hstack((result, mfccs))
        if chroma:
            chroma=np.mean(librosa.feature.chroma_stft(S=stft, sr=sample_rate).T,axis=0)
            result=np.hstack((result, chroma))
        if mel:
            mel=np.mean(librosa.feature.melspectrogram(X, sr=sample_rate).T,axis=0)
            result=np.hstack((result, mel))
        return result

emotions={
    '01':'neutral',
    '02':'calm',
    '03':'happy',
    '04':'sad',
    '05':'angry',
    '06':'fearful',
    '07':'disgust',
    '08':'surprised'
}
observed_emotions=['calm', 'happy', 'fearful', 'disgust']

def load_data(test_size=0.2):
    x,y=[],[]
    from google.colab import drive
    drive.mount('/gdrive', force_remount=True)
    for file in glob.glob(f"/gdrive/MyDrive/datatset/Actor_*/*.wav"):
        file_name=os.path.basename(file)
        emotion=emotions[file_name.split("-")[2]]
        if emotion not in observed_emotions:
            continue
        feature=extract_feature(file, mfcc=True, chroma=True, mel=True)
        x.append(feature)
        y.append(emotion)
    return train_test_split(np.array(x), y, test_size=test_size, random_state=9)

x_train,x_test,y_train,y_test=load_data(test_size=0.25)

以下是我收到的错误

Mounted at /gdrive
---------------------------------------------------------------------------
ParameterError                            Traceback (most recent call last)
<ipython-input-78-03a67f23ae57> in <module>()
----> 1 x_train,x_test,y_train,y_test=load_data(test_size=0.25)

3 frames
<ipython-input-77-e0a93a2717f9> in load_data(test_size)
      8                 if emotion not in observed_emotions:
      9                         continue
---> 10                 feature=extract_feature(file, mfcc=True, chroma=True, mel=True)
     11                 x.append(feature)
     12                 y.append(emotion)

<ipython-input-66-c2424d41c241> in extract_feature(file_name, mfcc, chroma, mel)
      4                 sample_rate=sound_file.samplerate
      5                 if chroma:
----> 6                         stft=np.abs(librosa.stft(X))
      7                 result=np.array([])
      8                 if mfcc:

/usr/local/lib/python3.7/dist-packages/librosa/core/spectrum.py in stft(y, n_fft, hop_length, win_length, window, center, dtype, pad_mode)
    215 
    216     # Check audio is valid
--> 217     util.valid_audio(y)
    218 
    219     # Pad the time series so that frames are centered

/usr/local/lib/python3.7/dist-packages/librosa/util/utils.py in valid_audio(y, mono)
    293         raise ParameterError(
    294             "Invalid shape for monophonic audio: "
--> 295             "ndim={:d}, shape={}".format(y.ndim, y.shape)
    296         )
    297 

ParameterError: Invalid shape for monophonic audio: ndim=2, shape=(172972, 2)

Answer 1

您得到的错误意味着您拥有的声音文件是立体声的。您需要将其更改为单声道。你应该试试这个。由于您在 Colab 中工作，因此您应该首先检查您是否可以导入 AudioSegment：

!pip install pydub
from google.colab import drive
import os
from pydub import AudioSegment

那么这应该可以工作

from pydub import AudioSegment
sound = AudioSegment.from_wav("The path to your file.wav")
sound = sound.set_channels(1)  ## This sets it to mono
sound.export("/output/path.wav", format="wav")