@inproceedings{deoras2011variational,
author = {Deoras, Anoop},
title = {Variational Approximation of Long-Span Language Models for LVCSR},
year = {2011},
month = {March},
abstract = {Long-span language models that capture syntax and semantics are seldom used in the first 
pass of large vocabulary continuous speech recognition systems due to the prohibitive 
search-space of sentencehypotheses. Instead, an N-best list of hypotheses is created 
using tractable n-gram models, and rescored using the long-span models. It is shown in 
this paper that computationally tractable variational approximations of the long-span 
models are a better choice than standard n-gram models for first pass decoding. They not 
only result in a better first pass output, but also produce a lattice with a lower oracle word 
error rate, and rescoring the N-best list from such lattices with the long-span models 
requires a smaller N to attain the same accuracy. Empirical results on the WSJ, MIT 
Lectures, NIST 2007 Meeting Recognition and NIST 2001 Conversational Telephone 
Recognition data sets are presented to support these claims.},
publisher = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
url = {http://approjects.co.za/?big=en-us/research/publication/variational-approximation-of-long-span-language-models-for-lvcsr/},
}