brain_pipe.preprocessing.stimulus.audio.spectrogram.LibrosaMelSpectrogram

class LibrosaMelSpectrogram(stimulus_data_key='stimulus_data', stimulus_sr_key='stimulus_sr', output_key='spectrogram_data', output_sr_key='spectrogram_sr', power_factor=1.0, sort_fn=None, librosa_kwargs={}, **kwargs)

Bases: PipelineStep

Calculates mel spectrogram using librosa.

Code was based on the ICASSP 2023 auditory EEG challenge: https://github.com/exporl/auditory-eeg-challenge-2023-code/blob/main/ task1_match_mismatch/util/mel_spectrogram.py

__init__(stimulus_data_key='stimulus_data', stimulus_sr_key='stimulus_sr', output_key='spectrogram_data', output_sr_key='spectrogram_sr', power_factor=1.0, sort_fn=None, librosa_kwargs={}, **kwargs)

Calculate the mel spectrogram of a raw speech file.

Parameters:

  • stimulus_data_key (str) – The key in the data dictionary that contains the stimulus data

  • stimulus_sr_key (str) – The key in the data dictionary that contains the stimulus sampling rate

  • output_key (str) – The key in the data dictionary to store the spectrogram

  • power_factor (float) – The power factor for each sample

  • sort_fn (Callable) – A function to sort the kwargs for librosa.feature.melspectrogram when when parsing the kwargs. This is useful when the callables are used that depend on other kwargs.

  • librosa_kwargs (Union[Dict[str, Any], Callable]) – Keyword arguments to pass to librosa.feature.melspectrogram. Can also be a callable that takes in data_dict and returns a dict of kwargs.

  • kwargs (dict) – Additional keyword arguments for the PipelineStep

Methods

__init__([stimulus_data_key, ...])

Calculate the mel spectrogram of a raw speech file.

parse_dict_keys(key[, name, ...])

Parse a key or a sequence of keys.

parse_librosa_kwargs(data_dict)

Parse kwargs for Librosa's melspectrogram function.
parse_dict_keys(key: str | Sequence[str] | Mapping[str, str], name='key', require_ordered_dict=False) → OrderedDict[str, str]

Parse a key or a sequence of keys.

Parameters:

  • key (Union[str, Sequence[str], Mapping[str,str]]) – A key or a sequence of keys.

  • name (str) – The name of the key. Used for error messages.

  • require_ordered_dict (bool) – If True, the key must be an OrderedDict. If False, the key can also be an ordinary dict.

Returns:

A mapping of input keys to output keys.

Return type:

OrderedDict[str, str]

Raises:

TypeError – If the key is not a string, a sequence of strings or a mapping of strings. If the key is a mapping but require_ordered_dict is True and the mapping is not an OrderedDict.

parse_librosa_kwargs(data_dict)

Parse kwargs for Librosa’s melspectrogram function.

Parameters:

data_dict (Dict[str, Any]) – The data dictionary

Returns:

The parsed kwargs for Librosa’s melspectrogram function

Return type:

Dict[str, Any]