sample.beatsdrop.sample module

Module for integrating BeatsDROP in the SAMPLE model

class sample.beatsdrop.sample.SAMPLEBeatsDROP(beatsdrop: ~typing.Optional[~sample.beatsdrop.regression.BeatRegression] = None, beat_decisor: ~typing.Optional[~sample.beatsdrop.decision.BeatDecisor] = None, sinusoidal: ~typing.Optional[~sample.sms.sm.SinusoidalModel] = None, regressor: ~typing.Optional[~sample.hinge.HingeRegression] = None, regressor_k: str = 'k_', regressor_q: str = 'q_', freq_reduce: ~typing.Callable[[~numpy.ndarray], float] = <function mean>, max_n_modes: ~typing.Optional[int] = None, **kwargs)

Bases: SAMPLE

SAMPLE model with BeatsDROP beat decoupling

Parameters:

• beatsdrop (BeatRegression) – Beat regression model. Default is an instance of sample.beatsdrop.regression.DualBeatRegression

• beat_decisor (BeatDecisor) – Model responsible for deciding wether the trajectory is a beat or not. By default it is an instance of sample.beatsdrop.decision.AlmostNotABeatDecisor

• sinusoidal (SinusoidalModel) – Sinusoidal analysis model. Default is an instance of sample.sms.mm.ModalModel

• regressor – Modal parameters regression model. Default is an instance of sample.hinge.HingeRegression

• regressor_k (str) – Attribute name for the estimated slope coefficient of regressor

• regressor_q (str) – Attribute name for the estimated intercept coefficient of regressor

• freq_reduce (callable) – Callable function for reducing the frequency track into a single frequency. Defaults to numpy.mean()

• max_n_modes (int) – Number of modes to use in resynthesis. If None (default), then synthesise all modes

• **kwargs – Additional parameters for sub-models. See sample.beatsdrop.regression.DualBeatRegression, sample.beatsdrop.decision.AlmostNotABeatDecisor, sample.sms.mm.ModalTracker, sample.sms.mm.ModalModel, sample.hinge.HingeRegression, and sample.utils.learn.OptionalStorage

param_matrix_

4-by-N matrix of modal parameters

Type:

array

property beat_decisor

Beat decision model

property beatsdrop

Beat regression model

property phases_: ndarray

Learned sinusoidal phases. Relevant between pairs of beating partials

predict(x: ndarray, **kwargs) → ndarray

Resynthesize audio

Parameters:

• x (array) – Time axis

• **kwargs – Keyword arguments for sample.sample.SAMPLE.predict()

Returns:

Array of audio samples

Return type:

array