Feature extraction¶

Spectral features¶

`spectral_centroid`(*[, y, sr, S, n_fft, ...])	Compute the spectral centroid.
`spectral_bandwidth`(*[, y, sr, S, n_fft, ...])	Compute p'th-order spectral bandwidth.
`spectral_rolloff`(*[, y, sr, S, n_fft, ...])	Compute roll-off frequency.
`spectral_flatness`(*[, y, S, n_fft, ...])	Compute spectral flatness.
`spectral_contrast`(*[, y, sr, S, n_fft, ...])	Compute spectral contrast.
`rms`(*[, y, S, frame_length, hop_length, ...])	Compute root-mean-square (RMS) value for each frame.
`zero_crossing_rate`(y, *[, frame_length, ...])	Compute the zero-crossing rate of an audio time series.

Mel-frequency representations¶

`melspectrogram`(*[, y, sr, S, n_fft, ...])	Compute a mel-scaled spectrogram.
`mfcc`(*[, y, sr, S, n_mfcc, dct_type, norm, ...])	Compute Mel-frequency cepstral coefficients (MFCCs).

Chromagram¶

`chroma_stft`(*[, y, sr, S, norm, n_fft, ...])	Compute a chromagram from a power spectrogram or waveform.
`chroma_cqt`(*[, y, sr, C, hop_length, fmin, ...])	Chromagram from a constant-Q transform.
`chroma_filter`(*, sr, n_fft[, n_chroma, ...])	Create a chroma filter bank.

Constant-Q transform¶

`cqt`(y, *[, sr, hop_length, fmin, n_bins, ...])	Compute the constant-Q transform following nnAudio's CQT1992v2 implementation.
`cqt2010`(y, *[, sr, hop_length, fmin, fmax, ...])	Compute constant-Q transform using the 2010 algorithm with multi-resolution.
`cqt_frequencies`(*[, n_bins, ...])	Compute the center frequencies of Constant-Q bins.

Tonal features¶

tonnetz(*[, y, sr, chroma])

Compute the tonal centroid features (tonnetz).

Pitch and frequency¶

`hz_to_octs`(frequencies, *[, tuning, ...])	Convert frequencies (Hz) to octave numbers.
`note_to_hz`()	Convert one or more note names to frequency (Hz).