recipes.cpc3.baseline package

Submodules

recipes.cpc3.baseline.compute_haspi module

Compute the HASPI scores.

recipes.cpc3.baseline.compute_haspi.compute_haspi_for_signal(record: dict, data_root: str, split: str) → float[source]

Compute the HASPI score for a given signal.

Parameters:

  • record (dict) – the metadata dict for the signal

  • signal_dir (str) – paths to where the HA output signals are stored

  • ref_dir (str) – path to where the reference signals are stored

Returns:

HASPI score

Return type:

float

recipes.cpc3.baseline.compute_haspi.parse_signal_name(signal_name: str) → dict[source]

Parse the signal name.

recipes.cpc3.baseline.compute_haspi.run_calculate_haspi(cfg: DictConfig) → None[source]

Run the HASPI score computation.

recipes.cpc3.baseline.compute_haspi.set_seed_with_string(seed_string: str) → None[source]

Set the random seed with a string.

recipes.cpc3.baseline.evaluate module

Evaluate the predictions against the ground truth correctness values

recipes.cpc3.baseline.evaluate.compute_scores(predictions, labels) → dict[source]

Compute the scores for the predictions

recipes.cpc3.baseline.evaluate.evaluate(cfg: DictConfig) → None[source]

Evaluate the predictions against the ground truth correctness values

recipes.cpc3.baseline.evaluate.kt_score(x: ndarray, y: ndarray) → float[source]

Compute the Kendall’s tau correlation between two arrays

recipes.cpc3.baseline.evaluate.ncc_score(x: ndarray, y: ndarray) → float[source]

Compute the normalized cross correlation between two arrays

recipes.cpc3.baseline.evaluate.rmse_score(x: ndarray, y: ndarray) → float[source]

Compute the root mean squared error between two arrays

recipes.cpc3.baseline.evaluate.std_err(x: ndarray, y: ndarray) → float[source]

Compute the standard error between two arrays

recipes.cpc3.baseline.predict_dev module

Make intelligibility predictions from HASPI scores.

recipes.cpc3.baseline.predict_dev.predict_dev(cfg: DictConfig)[source]

Predict intelligibility from HASPI scores.

recipes.cpc3.baseline.predict_train module

Make intelligibility predictions from HASPI scores.

recipes.cpc3.baseline.predict_train.predict_train(cfg: DictConfig)[source]

Predict intelligibility from HASPI scores.

recipes.cpc3.baseline.shared_predict_utils module

class recipes.cpc3.baseline.shared_predict_utils.LogisticModel[source]

Bases: object

Class to represent a logistic mapping.

Fits a logistic mapping from input values x to output values y.

fit(x, y)[source]

Fit a mapping from x values to y values.

params: ndarray | None = None
predict(x)[source]

Predict y values given x.

Raises:

TypeError – If the predict() method is called before fit().

recipes.cpc3.baseline.shared_predict_utils.load_dataset_with_haspi(cfg, split: str) → pandas.DataFrame[source]

Load dataset and add HASPI scores.

recipes.cpc3.baseline.shared_predict_utils.make_disjoint_train_set(full_df: pandas.DataFrame, test_df: pandas.DataFrame) → pandas.DataFrame[source]

Make a disjoint train set for given test samples.

Module contents