pyeeg.features.FeaturePipeline.extract_audio

FeaturePipeline.extract_audio(signal: ndarray, srate: float, signal_length: int | None = None) → Tuple[Dict[str, ndarray], Dict]

Extract acoustic features from an audio signal.

Runs every configured acoustic extractor over signal and collects the resulting features, prefixed with each extractor’s name.

Parameters:

• signal (ndarray) – Audio signal as a 1D numpy array.

• srate (float) – Sampling rate of the audio signal in Hz.

• signal_length (int, optional) – Reserved for compatibility with the text path; not used by acoustic extraction.

Returns:

• result (dict of str -> ndarray) – Feature name to array mapping. Keys are "{extractor_name}_{feature}".

• metadata (dict) – Metadata describing the extraction: stimulus_type ("audio"), sampling_rate (provided sampling rate), feature_specs (configured acoustic spec names), and n_samples (length of the input signal).