Caution

You're reading the documentation for a development version. For the latest released version, please have a look at 0.9.1.

librosa.feature.tonnetz

librosa.feature.tonnetz(*, y=None, sr=22050, chroma=None, **kwargs)[source]

Computes the tonal centroid features (tonnetz)

This representation uses the method of 1 to project chroma features onto a 6-dimensional basis representing the perfect fifth, minor third, and major third each as two-dimensional coordinates.

1

Harte, C., Sandler, M., & Gasser, M. (2006). “Detecting Harmonic Change in Musical Audio.” In Proceedings of the 1st ACM Workshop on Audio and Music Computing Multimedia (pp. 21-26). Santa Barbara, CA, USA: ACM Press. doi:10.1145/1178723.1178727.

Parameters
ynp.ndarray [shape=(…, n,)] or None

Audio time series. Multi-channel is supported.

srnumber > 0 [scalar]

sampling rate of y

chromanp.ndarray [shape=(n_chroma, t)] or None

Normalized energy for each chroma bin at each frame.

If None, a cqt chromagram is performed.

**kwargs

Additional keyword arguments to chroma_cqt, if chroma is not pre-computed.

Returns
tonnetznp.ndarray [shape(…, 6, t)]

Tonal centroid features for each frame.

Tonnetz dimensions:
  • 0: Fifth x-axis

  • 1: Fifth y-axis

  • 2: Minor x-axis

  • 3: Minor y-axis

  • 4: Major x-axis

  • 5: Major y-axis

See also

chroma_cqt

Compute a chromagram from a constant-Q transform.

chroma_stft

Compute a chromagram from an STFT spectrogram or waveform.

Examples

Compute tonnetz features from the harmonic component of a song

>>> y, sr = librosa.load(librosa.ex('nutcracker'), duration=10, offset=10)
>>> y = librosa.effects.harmonic(y)
>>> tonnetz = librosa.feature.tonnetz(y=y, sr=sr)
>>> tonnetz
array([[ 0.007, -0.026, ...,  0.055,  0.056],
       [-0.01 , -0.009, ..., -0.012, -0.017],
       ...,
       [ 0.006, -0.021, ..., -0.012, -0.01 ],
       [-0.009,  0.031, ..., -0.05 , -0.037]])

Compare the tonnetz features to chroma_cqt

>>> import matplotlib.pyplot as plt
>>> fig, ax = plt.subplots(nrows=2, sharex=True)
>>> img1 = librosa.display.specshow(tonnetz,
...                                 y_axis='tonnetz', x_axis='time', ax=ax[0])
>>> ax[0].set(title='Tonal Centroids (Tonnetz)')
>>> ax[0].label_outer()
>>> img2 = librosa.display.specshow(librosa.feature.chroma_cqt(y=y, sr=sr),
...                                 y_axis='chroma', x_axis='time', ax=ax[1])
>>> ax[1].set(title='Chroma')
>>> fig.colorbar(img1, ax=[ax[0]])
>>> fig.colorbar(img2, ax=[ax[1]])
../_images/librosa-feature-tonnetz-1.png