Bayesian compressive sensing for phonetic classification
Tara N. Sainath, Avishy Carmi, et al.
ICASSP 2010
Language model pruning is an essential technology for speech applications running on resource-constrained devices, and many pruning algorithms have been developed for conventional word n-gram models. However, while exponential language models can give superior performance, there has been little work on the pruning of these models. In this paper, we propose several pruning algorithms for general exponential language models. We show that our best algorithm applied to an exponential n-gram model outperforms existing n-gram model pruning algorithms by up to 0.4% absolute in speech recognition word-error rate on Wall Street Journal and Broadcast News data sets. In addition, we show that Model M, an exponential class-based language model, retains its performance improvement over conventional word n-gram models when pruned to equal size, with gains of up to 2.5% absolute in word-error rate. © 2011 IEEE.
Tara N. Sainath, Avishy Carmi, et al.
ICASSP 2010
Saurabh Paul, Christos Boutsidis, et al.
JMLR
C.A. Micchelli, W.L. Miranker
Journal of the ACM
Joxan Jaffar
Journal of the ACM