Viet-Anh on Software Logo

What is: Local Prior Matching?

SourceSemi-Supervised Speech Recognition via Local Prior Matching
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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_yx=pˉ_yxq\_{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.