Study on interaction between entropy pruning and kneser-ney smoothing

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.

• Type: Journal
• Year: 2010
• Where: INTERSPEECH
• Authors: Ciprian Chelba, Thorsten Brants, Will Neveitt, Peng Xu
• Keywords: Aggressive Pruning Regimes, Entropy Pruning, INTERSPEECH 2010, Pruning, Signal Processing