Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
audio feature extraction method
|
| gptkbp:appliesTo |
gptkb:Short-Time_Fourier_Transform
mel filter bank |
| gptkbp:basedOn |
mel scale
|
| gptkbp:featureType |
time-frequency representation
|
| https://www.w3.org/2000/01/rdf-schema#label |
MelSpectrogram
|
| gptkbp:implementedIn |
gptkb:TensorFlow
gptkb:PyTorch Librosa |
| gptkbp:input |
audio signal
|
| gptkbp:output |
spectrogram
|
| gptkbp:parameter |
hop_length
n_fft n_mels |
| gptkbp:relatedTo |
gptkb:MFCC
gptkb:Spectrogram Chroma feature |
| gptkbp:transformsInto |
frequency axis
|
| gptkbp:usedFor |
audio synthesis
audio classification voice activity detection music genre recognition sound event detection |
| gptkbp:usedIn |
gptkb:music_information_retrieval
speech recognition |
| gptkbp:visualizes |
2D image
|
| gptkbp:bfsParent |
gptkb:torchaudio
|
| gptkbp:bfsLayer |
6
|