Thermodynamic properties of nickel?selenium alloys

Jelinek, H.F.; Komarek, K. L.

doi:10.1007/bf00910257

Cited by 10 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors would like to thank especially Enrique Vidal from Universidad PolitCcnica de Valencia for much helpful advice. lution to the "lack of samples" problem [4]. A way to give a solution to this problem for the proposed syntactic approach consists of the translation of the solutions developed for the N-gram approach.…”

Section: Introductionmentioning

confidence: 99%

K-TLSS(S) language models for speech recognition

Bordel

Varona

Torres

1997 IEEE International Conference on Acoustics, Speech, and Signal Processing

View full text Add to dashboard Cite

The class of K-Testable Languages in the Strict Sense (K-TLSS) is a subclass of regular languages. Previous works demonstrate that stochastic K-TLSS language models describe the same probability distribution as N-gram models, and that smoothing techniques can be efficiently applied (Back-off like methods). Once we have a set of k-TLSS models (k = 1. . . K) and a smoothing technique that specifically fits in them, here we propose an integration into a unique self-contained model (the K-TLSS( S)) which embeds the smoothing within the topology allowing extremely simple parsing procedures. To build this model we designed a more general syntactic mechanism that we call Stochastic Deterministic Finite State Automaton with Recursive Transitions. The topology of the new models (K-TLSS(S)) allows an easy pruning procedure. Pruned K-TLSS(S) models give probability distributions that are equivalent to Variable length N-gram models. Experimental results gave as a conclusion that the effect of a small pruning is always positive.

show abstract

Section: Introductionmentioning

confidence: 99%