Semi-Supervised Learning Methods

Local Prior Matching

Introduced by Hsu et al. in Semi-Supervised Speech Recognition via Local Prior Matching

Local Prior Matching is a semi-supervised objective for speech recognition that distills knowledge from a strong prior (e.g. a language model) to provide learning signal to a discriminative model trained on unlabeled speech. The LPM objective minimizes the cross entropy between the local prior and the model distribution, and is minimized when $q_{y\mid{x}} = \bar{p}_{y\mid{x}}$. Intuitively, LPM encourages the ASR model to assign posterior probabilities proportional to the linguistic probabilities of the proposed hypotheses.

Source: Semi-Supervised Speech Recognition via Local Prior Matching

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Learning with noisy labels 1 16.67%
Meta-Learning 1 16.67%
Node Classification 1 16.67%
Knowledge Distillation 1 16.67%
Language Modelling 1 16.67%
Speech Recognition 1 16.67%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories