IvectorConfigMixin#

class montreal_forced_aligner.corpus.features.IvectorConfigMixin(num_gselect=20, posterior_scale=1.0, min_post=0.025, max_count=100, **kwargs)[source]#

Bases: VadConfigMixin

Mixin class for ivector features

Parameters:

ivector_dimension (int) – Dimension of ivectors
num_gselect (int) – Gaussian-selection using diagonal model: number of Gaussians to select
posterior_scale (float) – Scale on the acoustic posteriors, intended to account for inter-frame correlations
min_post (float) – Minimum posterior to use (posteriors below this are pruned out)
max_count (int) – The use of this option (e.g. –max-count 100) can make iVectors more consistent for different lengths of utterance, by scaling up the prior term when the data-count exceeds this value. The data-count is after posterior-scaling, so assuming the posterior-scale is 0.1, –max-count 100 starts having effect after 1000 frames, or 10 seconds of data.