The process of understanding spoken language requires the efficient processing of ambiguities that arise by the nature of speech. This paper presents an approach that allows the efficient incremental integration of speech recognition and language understanding using Tomita's generalized LR-parsing algorithm. For this purpose the GLRlattice -parsing-algorithm [11] is revised so that an agenda mechanism can be used to control the flow of computation of the parsing process. Subsequently the HMMevaluations of the word models are combined with a stochastical language model to do a beam search similar to [2, 1, 12], where chartparsers are used to do the job. 1. INTRODUCTION In [10] M. Tomita proposes a parsing algorithm (Generalized LR-Parsing, GLRP) and extends it in [11] to an algorithm that can parse whole word lattices. This algorithm often works more efficiently with grammars for natural languages than others (see [10, 7]). Nevertheless the lattice-GLRP is not very flexible and require...

We outline an implementation of Viterbi beam search that incorporates layered bigrams. Layered bigrams are class bigrams in which some nodes are themselves bigrams, resulting in a recursive structure. The implementation is in C ++ and involves a hierarchy of classes. The paper outlines the main concepts and the corresponding C ++ classes.

Abstract—This paper presents the time-conditioned approach in dynamic programming search for large-vocabulary continuousspeech recognition. The following topics are presented: the baseline algorithm, a time-synchronous beam search version, a comparison with the word-conditioned approach, a comparison with stack decoding. The approach has been successfully tested on the NAB task using a vocabulary of 64 000 words. Index Terms—Beam search, dynamic programming, large vocabulary speech recognition, one-pass DP search, search organization, time-conditioned DP search. I.

This diploma thesis investigates appearance-based features for the person-independent vision-based recognition of continuous sign language. A large variety of methods which have been successfully used for automatic speech recognition is applied to this task. Appearance-based approaches do not rely on a segmentation of the images or on predefined models of the image content and use the image itself as the feature. A novel tracking algorithm is introduced and applied to hand and head tracking. The tracked body parts are used in order to calculate additional features to improve recognition performance. The presented automatic sign language recognition system is evaluated on a set of sentences in American Sign Language.