dlpy.audio.AudioTable.extract_audio_features¶
-
classmethod
AudioTable.extract_audio_features(conn, table, frame_shift=10, frame_length=25, n_bins=40, n_ceps=40, feature_scaling_method='STANDARDIZATION', n_output_frames=500, casout=None, random_shuffle=True, **kwargs)¶ Extracts audio features from the audio files
- Parameters
- connCAS
A connection object to the current session.
- tableAudioTable
An audio table containing the audio files.
- frame_shiftint, optional
Specifies the time difference (in milliseconds) between the beginnings of consecutive frames. Default: 10
- frame_lengthint, optional
Specifies the length of a frame (in milliseconds). Default: 25
- n_binsint, optional
Specifies the number of triangular mel-frequency bins. Default: 40
- n_cepsint, optional
Specifies the number of cepstral coefficients in each MFCC feature frame (including C0). Default: 40
- feature_scaling_methodstring, optional
Specifies the feature scaling method to apply to the computed feature vectors. Default: ‘standardization’
- n_output_framesint, optional
Specifies the exact number of frames to include in the output table (extra frames are dropped and missing frames are padded with zeros). Default: 500
- casoutdict or string or CASTable, optional
CAS Output table
- random_shufflebool, optional
Specifies whether shuffle the generated CAS table randomly. Default: True
- kwargskeyword-arguments, optional
Additional parameter for feature extraction. For details, see the documentation for audio.computeFeatures.
- Returns
AudioTableIf table exists
- None
If no table exists