@inproceedings{,
author={Gosztolya, G{\'a}bor and Kocsor, Andr{\'a}s},
title={Aggregation Operators and Hypothesis Space Reductions in Speech Recognition},
abstract={In this paper we deal with the heuristic exploration of general hypothesis
spaces arising both in the HMM and segment-based approaches of speech recognition.
The generated hypothesis space is a tree where we assign costs to its nodes.
The tree and the costs are both generated in a top-down way where we have
node extension rules and aggregation operators for the cost calculation.
We introduce a special set of mean aggregation operators suitable for speech
recognition tasks. Then we discuss the efficiency of some heuristic search
methods like the Viterbi beam search, multi-stack decoding algorithm, and
some improvements using these aggregation operators. The tests showed that
this technique could significantly speed up the recognition process. The
run-times we obtained were 2 times faster than the basic multi-stack decoding
method, and 4 times faster than the Viterbi beam search method.},
booktitle={Proceedings of the Seventh International Conference on Text, Speech, Dialogue,
TSD 2004, LNAI vol. 3206},
year={2004},
month={September},
publisher={Springer-Verlag GmbH},
address={Brno, Czech Republic},
editor={Petr Sojka, Ivan Kopecek, Karel Pala},
pages={315-322}
}