utils

Utilities for data generation.

clarity.data.utils.better_ear_speechweighted_snr(target: ndarray, noise: ndarray) → float

Calculate effective better ear SNR.

Parameters:

• target (np.ndarray)

• noise (np.ndarray)

Returns:

(float)

Maximum Signal Noise Ratio between left and right channel.

clarity.data.utils.pad(signal: ndarray, length: int) → ndarray

Zero pad signal to required length.

Assumes required length is not less than input length.

Parameters:

• signal (np.array)

• length (int)

Return type:

np.array

clarity.data.utils.speechweighted_snr(target: ndarray, noise: ndarray) → float

Apply speech weighting filter to signals and get SNR.

Parameters:

• target (np.ndarray)

• noise (np.ndarray)

Return type:

(float)

Signal Noise Ratio

clarity.data.utils.sum_signals(signals: list) → ndarray | Literal[0]

Return sum of a list of signals.

Signals are stored as a list of ndarrays whose size can vary in the first dimension, i.e., so can sum mono or stereo signals etc. Shorter signals are zero padded to the length of the longest.

Parameters:

signals (list) – List of signals stored as ndarrays

Returns:

The sum of the signals

Return type:

np.ndarray