RMSEnvelope#

Defined in: voxatlas.features.acoustic.envelope.rms

class voxatlas.features.acoustic.envelope.rms.RMSEnvelope[source]#

Bases: BaseExtractor

Extract the acoustic.envelope.rms feature within the VoxAtlas pipeline.

Computes a smoothed, frame-aligned root-mean-square (RMS) amplitude envelope from the raw waveform.

Algorithm#

The extractor computes a frame-level root-mean-square amplitude envelope from the waveform.

  1. Frame extraction The signal is segmented into overlapping windows determined by frame_length and frame_step.

  2. Energy accumulation For each frame \(x_t[n]\), the envelope value is

    \[\mathrm{RMS}_t = \sqrt{\frac{1}{N}\sum_{n=1}^{N} x_t[n]^2}.\]

  3. Output alignment RMS values are returned with frame midpoints so that derived features such as derivatives, onsets, and peak rate can reuse the same temporal grid.

name#

Registry key for this extractor ("acoustic.envelope.rms").

Type:

str

input_units#

Required input unit level. None means this extractor operates directly on waveform audio.

Type:

str | None

output_units#

Output alignment unit ("frame").

Type:

str | None

dependencies#

Upstream features required before execution. Empty for this extractor.

Type:

list[str]

default_config#

Default runtime parameters: frame_length=0.025, frame_step=0.01, peak_threshold=0.1, smoothing=1.

Type:

dict

References

Rabiner, L., & Schafer, R. (2011). Theory and Applications of Digital Speech Processing. Pearson.

Examples

>>> import numpy as np
>>> from voxatlas.audio.audio import Audio
>>> from voxatlas.features.acoustic.envelope.rms import RMSEnvelope
>>> from voxatlas.features.feature_input import FeatureInput
>>> audio = Audio(waveform=np.zeros(1600, dtype=np.float32), sample_rate=16000)
>>> feature_input = FeatureInput(audio=audio, units=None, context={})
>>> params = RMSEnvelope.default_config.copy()
>>> out = RMSEnvelope().compute(feature_input, params)
>>> out.unit
'frame'
name: str = 'acoustic.envelope.rms'#
input_units: str | None = None#
output_units: str | None = 'frame'#
dependencies: list[str] = []#
default_config: dict = {'frame_length': 0.025, 'frame_step': 0.01, 'peak_threshold': 0.1, 'smoothing': 1}#
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.envelope.rms import RMSEnvelope
>>> from voxatlas.features.feature_input import FeatureInput
>>> audio = Audio(waveform=np.zeros(1600, dtype=np.float32), sample_rate=16000)
>>> feature_input = FeatureInput(audio=audio, units=None, context={})
>>> params = RMSEnvelope.default_config.copy()
>>> result = RMSEnvelope().compute(feature_input, params)
>>> result.values.shape[0] > 0
True