No abstract

No abstract

No abstract

ABS'IRACT. In this paper. we study various problems related to smoothing bigram probabilities for natural language modelling: the type of interpolation. i.e. linear vs. nonlinear, the optimal estimation of interpolation parameters, and the use of word equivalence classes @arts of speech).We design a new nonlinear interpolation method that resulu in significant improvements over linear interpolation in the experimental tests. It is shown that the leaving-one-out method in combination with the maximum likelihood criterion can be efficiently used for the optimal estimation of interpolation parameters. In addition, an automatic clustering procedure is developed for finding word equivalence classes using a maximum likelihood criterion. Experimental results are presented for two text databases: a German database with 1OO.OOO words and an English database with 1.1 million words.

This paper gives an overview of a research system for phoneme based, large vocabulary continuous speech recognition. The system to be described has been applied to the SPICOS task, the DARPA RM task and a 12000 word dictation task. Experimental results for these three tasks will be presented. Like many other systems, the recognition architecture is based on an integrated statistical approach. In this paper, we describe the characteristic features of the system as opposed to other systems: (1) The Viterbi criterion is consistently applied both in training and testing. (2) Continuous mixture densities are used without any tying or smoothing; this approach can be viewed as a sort of ‘statistical template matching’. (3) Time-synchronous beam search is used consistently throughout all tasks; extensions using a tree organization of the vocabulary and phoneme lookahead are presented so that a 12000 word task can be handled.