Caution
You're reading the documentation for a development version. For the latest released version, please have a look at 0.9.1.
Feature extraction¶
Spectral features¶
|
Compute a chromagram from a waveform or power spectrogram. |
|
Constant-Q chromagram |
|
Computes the chroma variant "Chroma Energy Normalized" (CENS) |
|
Compute a mel-scaled spectrogram. |
|
Mel-frequency cepstral coefficients (MFCCs) |
|
Compute root-mean-square (RMS) value for each frame, either from the audio samples |
|
Compute the spectral centroid. |
|
Compute p'th-order spectral bandwidth. |
|
Compute spectral contrast |
|
Compute spectral flatness |
|
Compute roll-off frequency. |
|
Get coefficients of fitting an nth-order polynomial to the columns of a spectrogram. |
|
Computes the tonal centroid features (tonnetz) |
|
Compute the zero-crossing rate of an audio time series. |
Rhythm features¶
|
Compute the tempogram: local autocorrelation of the onset strength envelope. |
|
Compute the Fourier tempogram: the short-time Fourier transform of the onset strength envelope. |
Feature manipulation¶
|
Compute delta features: local estimate of the derivative of the input data along the selected axis. |
|
Short-term history embedding: vertically concatenate a data vector or matrix with delayed copies of itself. |
Feature inversion¶
|
Approximate STFT magnitude from a Mel power spectrogram. |
|
Invert a mel power spectrogram to audio using Griffin-Lim. |
|
Invert Mel-frequency cepstral coefficients to approximate a Mel power spectrogram. |
|
Convert Mel-frequency cepstral coefficients to a time-domain audio signal |