Abstract:
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to cap...Show MoreMetadata
Abstract:
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture important regularities in the data. Several possible solutions were proposed, namely class based models, factored models, decision trees and neural networks. This paper describes improvements obtained in recognition of spoken Czech lectures using language models based on neural networks. Relative reductions in word error rate are more than 15% over baseline obtained with adapted 4-gram backoff language model using modified Kneser-Ney smoothing.
Date of Conference: 19-24 April 2009
Date Added to IEEE Xplore: 26 May 2009
ISBN Information: