๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Minimization of the generalized error functional in recognition algorithms

โœ Scribed by V.I. Ishchuk

Publisher
Elsevier Science
Year
1978
Weight
316 KB
Volume
18
Category
Article
ISSN
0041-5553

No coin nor oath required. For personal study only.

๐Ÿ“œ SIMILAR VOLUMES

In Favor of Conjugate Directions: a Gene
In Favor of Conjugate Directions: a Generalized Acceptable-point Algorithm for Function Minimization
โœ M.A. Townsend; G.E. Johnson ๐Ÿ“‚ Article ๐Ÿ“… 1978 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 915 KB

## A generalization of the conjugate directions minimization technique enables utilization of a coarse univariate subsearch to identify acceptable points (as opposed to a minimizing line search) and performs better than commonly-used conjugate directions algorithms. It performs comparably to and has

Finding consensus in speech recognition:
Finding consensus in speech recognition: word error minimization and other applications of confusion networks
โœ Lidia Mangu; Eric Brill; Andreas Stolcke ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 374 KB

We describe a new framework for distilling information from word lattices to improve the accuracy of the speech recognition output and obtain a more perspicuous representation of a set of alternative hypotheses. In the standard MAP decoding approach the recognizer outputs the string of words corresp