mne_denoise.asr.process_guided_asr

mne_denoise.asr.process_guided_asr(X: ndarray, sfreq: float, state: ASRState, *, artifact_cov: ndarray | None = None, preserve_cov: ndarray | None = None, reconstruction: str = 'soft', guidance_strength: float = 1.0, window_length: float = 0.5, window_overlap: float = 0.66, max_dims: float | int = 0.66, regularization: float = 1e-08, store_reconstruction_matrices: bool = False, max_mem_mb: int | None = 512, lookahead: float | None = None, stepsize: int | None = None, callback=None, verbose: bool | str | int | None = None) → tuple[ndarray, dict[str, Any]]

Apply a calibrated ASR state with guided reconstruction.

Parameters:

Xndarray, shape (n_channels, n_times)

Continuous data in the calibrated channel order.

sfreqfloat

Sampling frequency in Hz.

stateASRState

Calibration state returned by calibrate_asr.

artifact_covndarray, shape (n_channels, n_channels), or None, default=None

Covariance describing directions to attenuate.

preserve_covndarray, shape (n_channels, n_channels), or None, default=None

Covariance describing directions to preserve.

reconstruction{“soft”, “hard”}, default=”soft”

Use guidance-aware continuous weights or standard binary ASR weights.

guidance_strengthfloat, default=1.0

Guidance contribution in [0, 1].

window_lengthfloat, default=0.5

Processing window length in seconds.

window_overlapfloat, default=0.66

Processing-window overlap.

max_dimsfloat or int, default=0.66

Maximum fraction or number of reconstructed components.

regularizationfloat, default=1e-8

Relative covariance eigenvalue floor.

store_reconstruction_matricesbool, default=False

Include reconstruction matrices in diagnostics.

max_mem_mbint or None, default=512

Memory bound for covariance processing.

lookaheadfloat or None, default=None

Processing lookahead in seconds.

stepsizeint or None, default=None

Samples between reconstruction updates.

callbackcallable or None, default=None

Synchronous progress callback.

verbosebool, str, int, or None, default=None

Logging level.

Returns:

X_cleanndarray, shape (n_channels, n_times)

Reconstructed data.

diagnosticsdict

ASR diagnostics with guided weights and reconstruction mode.

Notes

Hard reconstruction requires both guidance covariances to be None. Soft reconstruction requires the GuidedASR experimental opt-in when used through the estimator.