ShimmerExtractor#

Defined in: voxatlas.features.acoustic.voice_quality.shimmer

class voxatlas.features.acoustic.voice_quality.shimmer.ShimmerExtractor[source]#

Bases: BaseExtractor

Extract the acoustic.voice_quality.shimmer feature within the VoxAtlas pipeline.

This public extractor defines the reusable API for computing acoustic.voice_quality.shimmer from VoxAtlas structured inputs. It consumes None units and produces values aligned to frame units, making the extractor a stable pipeline node that can be cited independently of the surrounding execution machinery.

Algorithm#

The extractor estimates frame-to-frame amplitude perturbation using the \(f_0\) contour to define valid voiced regions.

  1. Framewise amplitude extraction The waveform is partitioned to match the number of \(f_0\) frames, and each voiced frame is summarized by its peak absolute amplitude \(A_t\).

  2. Relative perturbation Shimmer is computed as

    \[S_t = \frac{|A_t - A_{t-1}|}{\max(A_{t-1}, \varepsilon)}.\]

  3. Packaging The perturbation contour is kept at frame resolution for later summary statistics.

Notes

This extractor declares the upstream dependencies [‘acoustic.pitch.f0’] and is executed only after those features are available in the pipeline feature store.

Examples

>>> import numpy as np
>>> from voxatlas.audio.audio import Audio
>>> from voxatlas.features.acoustic.voice_quality.shimmer import ShimmerExtractor
>>> from voxatlas.features.feature_input import FeatureInput
>>> from voxatlas.features.feature_output import VectorFeatureOutput
>>> from voxatlas.pipeline.feature_store import FeatureStore
>>> audio = Audio(waveform=np.zeros(1600, dtype=np.float32), sample_rate=16000)
>>> store = FeatureStore()
>>> f0_out = VectorFeatureOutput(
...     feature="acoustic.pitch.f0",
...     unit="frame",
...     time=np.array([0.0, 0.01, 0.02, 0.03], dtype=np.float32),
...     values=np.array([100.0, 100.0, 100.0, 100.0], dtype=np.float32),
... )
>>> store.add("acoustic.pitch.f0", f0_out)
>>> feature_input = FeatureInput(audio=audio, units=None, context={"feature_store": store})
>>> out = ShimmerExtractor().compute(feature_input, {})
>>> (np.isnan(out.values[0]), out.values[1:].tolist())
(True, [0.0, 0.0, 0.0])
name: str = 'acoustic.voice_quality.shimmer'#
input_units: str | None = None#
output_units: str | None = 'frame'#
dependencies: list[str] = ['acoustic.pitch.f0']#
default_config: dict = {}#
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 frame unit level when applicable.

Return type:

FeatureOutput

Examples

>>> import numpy as np
>>> from voxatlas.audio.audio import Audio
>>> from voxatlas.features.acoustic.voice_quality.shimmer import ShimmerExtractor
>>> from voxatlas.features.feature_input import FeatureInput
>>> from voxatlas.features.feature_output import VectorFeatureOutput
>>> from voxatlas.pipeline.feature_store import FeatureStore
>>> audio = Audio(waveform=np.zeros(1600, dtype=np.float32), sample_rate=16000)
>>> store = FeatureStore()
>>> f0_out = VectorFeatureOutput(
...     feature="acoustic.pitch.f0",
...     unit="frame",
...     time=np.array([0.0, 0.01], dtype=np.float32),
...     values=np.array([100.0, 100.0], dtype=np.float32),
... )
>>> store.add("acoustic.pitch.f0", f0_out)
>>> feature_input = FeatureInput(audio=audio, units=None, context={"feature_store": store})
>>> result = ShimmerExtractor().compute(feature_input, {})
>>> result.unit
'frame'