ArticulatoryFeaturesExtractor#

Defined in: voxatlas.features.phonology.articulatory.features

class voxatlas.features.phonology.articulatory.features.ArticulatoryFeaturesExtractor[source]#

Bases: BaseExtractor

Extract the phonology.articulatory.features feature within the VoxAtlas pipeline.

This public extractor defines the reusable API for computing phonology.articulatory.features from VoxAtlas structured inputs. It consumes phoneme units and produces values aligned to phoneme units, making the extractor a stable pipeline node that can be cited independently of the surrounding execution machinery.

Algorithm#

The extractor maps phoneme labels to articulatory classes using the phonology resource tables bundled with VoxAtlas.

  1. Resource lookup Each aligned phoneme label is normalized to IPA-like form and matched against the articulatory feature inventory.

  2. Class projection The output is a binary or categorical indicator, typically representable as \(x_i = \mathbf{1}[\mathrm{phoneme}_i \in C]\) for a class \(C\) such as vowels, nasals, or plosives.

  3. Packaging The resulting phoneme-aligned values can then be aggregated into rhythm or segmental summaries.

Examples

>>> import pandas as pd
>>> from voxatlas.features.feature_input import FeatureInput
>>> from voxatlas.features.phonology.articulatory.features import ArticulatoryFeaturesExtractor
>>> from voxatlas.units import Units
>>> phonemes = pd.DataFrame(
...     {"id": [1, 2], "start": [0.0, 0.1], "end": [0.1, 0.2], "label": ["a", "p"]}
... )
>>> units = Units(phonemes=phonemes)
>>> params = ArticulatoryFeaturesExtractor.default_config.copy()
>>> out = ArticulatoryFeaturesExtractor().compute(FeatureInput(audio=None, units=units, context={}), params)
>>> out.unit
'phoneme'
>>> "vowel" in out.values.columns
True
name: str = 'phonology.articulatory.features'#
input_units: str | None = 'phoneme'#
output_units: str | None = 'phoneme'#
dependencies: list[str] = []#
default_config: dict = {'language': None, 'resource_root': None}#
compute(feature_input, params)[source]#

Compute the extractor output for a single pipeline invocation.

This method is the reusable execution entry point for the extractor. It receives the standard FeatureInput bundle, applies the configured algorithm, and returns feature values aligned to the extractor output units for storage in the pipeline feature store.

Parameters:

  • feature_input (object) – Structured extractor input bundling audio, hierarchical units, and execution context for this feature computation.

  • params (object) – Resolved feature configuration for this invocation. Keys are feature-specific and merged from defaults and pipeline settings.

Returns:

Structured output aligned to the phoneme unit level when applicable.

Return type:

FeatureOutput

Examples

>>> import pandas as pd
>>> from voxatlas.features.feature_input import FeatureInput
>>> from voxatlas.features.phonology.articulatory.features import ArticulatoryFeaturesExtractor
>>> from voxatlas.units import Units
>>> phonemes = pd.DataFrame({"id": [1], "start": [0.0], "end": [0.1], "label": ["a"]})
>>> units = Units(phonemes=phonemes)
>>> params = ArticulatoryFeaturesExtractor.default_config.copy()
>>> result = ArticulatoryFeaturesExtractor().compute(FeatureInput(audio=None, units=units, context={}), params)
>>> result.values.shape[0]
1