Distributed Discriminative Language Models for Google Voice Search

Preethi Jyothi
Brian Strope
Proceedings of ICASSP 2012, IEEE, pp. 5017-5021
Google Scholar

Abstract

This paper considers large-scale linear discriminative language models trained using a distributed perceptron algorithm. The algorithm is implemented efficiently using a
MapReduce/SSTable framework. This work also introduces the use of large amounts of unsupervised data (confidence filtered Google voice-search logs) in conjunction with a novel training procedure that regenerates word lattices for the given data with a weaker acoustic model than the one used to generate the unsupervised transcriptions for the logged data. We observe small but statistically significant improvements in recognition performance after reranking N-best lists of a standard Google voice-search data set.

Research Areas