madmom.audio.chroma¶
This module contains chroma related functionality.
-
class
madmom.audio.chroma.DeepChromaProcessor(fmin=65, fmax=2100, unique_filters=True, models=None, **kwargs)[source]¶ Compute chroma vectors from an audio file using a deep neural network that focuses on harmonically relevant spectral content.
Parameters: - fmin : int, optional
Minimum frequency of the filterbank [Hz].
- fmax : float, optional
Maximum frequency of the filterbank [Hz].
- unique_filters : bool, optional
Indicate if the filterbank should contain only unique filters, i.e. remove duplicate filters resulting from insufficient resolution at low frequencies.
- models : list of filenames, optional
List of model filenames.
Notes
Provided model files must be compatible with the processing pipeline and the values of fmin, fmax, and unique_filters. The general use case for the models parameter is to use a specific model instead of an ensemble of all models.
The models shipped with madmom differ slightly from those presented in the paper (less hidden units, narrower frequency band for spectrogram), but achieve similar results.
References
[1] Filip Korzeniowski and Gerhard Widmer, “Feature Learning for Chord Recognition: The Deep Chroma Extractor”, Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR), 2016. Examples
Extract a chroma vector using the deep chroma extractor:
>>> dcp = DeepChromaProcessor() >>> chroma = dcp('tests/data/audio/sample2.wav') >>> chroma array([[0.01317, 0.00721, ..., 0.00546, 0.00943], [0.36809, 0.01314, ..., 0.02213, 0.01838], ..., [0.1534 , 0.06475, ..., 0.00896, 0.05789], [0.17513, 0.0729 , ..., 0.00945, 0.06913]], dtype=float32) >>> chroma.shape (41, 12)
-
class
madmom.audio.chroma.CLPChroma(data, fps=50, fmin=27.5, fmax=4200.0, compression_factor=100, norm=True, threshold=0.001, **kwargs)[source]¶ Compressed Log Pitch (CLP) chroma as proposed in [1] and [2].
Parameters: - data : str, Signal, or SemitoneBandpassSpectrogram
Input data.
- fps : int, optional
Desired frame rate of the signal [Hz].
- fmin : float, optional
Lowest frequency of the spectrogram [Hz].
- fmax : float, optional
Highest frequency of the spectrogram [Hz].
- compression_factor : float, optional
Factor for compression of the energy.
- norm : bool, optional
Normalize the energy of each frame to one (divide by the L2 norm).
- threshold : float, optional
If the energy of a frame is below a threshold, the energy is equally distributed among all chroma bins.
Notes
The resulting chromagrams differ slightly from those obtained by the MATLAB chroma toolbox [2] because of different resampling and filter methods.
References
[1] (1, 2) Meinard Müller, “Information retrieval for music and motion”, Springer, 2007. [2] (1, 2, 3) Meinard Müller and Sebastian Ewert, “Chroma Toolbox: MATLAB Implementations for Extracting Variants of Chroma-Based Audio Features”, Proceedings of the International Conference on Music Information Retrieval (ISMIR), 2011.
-
class
madmom.audio.chroma.CLPChromaProcessor(fps=50, fmin=27.5, fmax=4200.0, compression_factor=100, norm=True, threshold=0.001, **kwargs)[source]¶ Compressed Log Pitch (CLP) Chroma Processor.
Parameters: - fps : int, optional
Desired frame rate of the signal [Hz].
- fmin : float, optional
Lowest frequency of the spectrogram [Hz].
- fmax : float, optional
Highest frequency of the spectrogram [Hz].
- compression_factor : float, optional
Factor for compression of the energy.
- norm : bool, optional
Normalize the energy of each frame to one (divide by the L2 norm).
- threshold : float, optional
If the energy of a frame is below a threshold, the energy is equally distributed among all chroma bins.