Study on Interaction between Entropy Pruning and Kneser-Ney Smoothing
Venue
Proceedings of Interspeech (2010), pp. 2242-2245
Publication Year
2010
Authors
Ciprian Chelba, Thorsten Brants, Will Neveitt, Peng Xu
BibTeX
Abstract
The paper presents an in-depth analysis of a less known interaction between
Kneser-Ney smoothing and entropy pruning that leads to severe degradation in
language model performance under aggressive pruning regimes. Experiments in a
data-rich setup such as google.com voice search show a significant impact in WER as
well: pruning Kneser-Ney and Katz models to 0.1% of their original impacts speech
recognition accuracy significantly, approx. 10% relative. Any third party with LDC
membership should be able to reproduce our experiments using the scripts available
at http://code.google.com/p/kneser-ney-pruning-experiments.
