file.pdf (154.89 kB)
0/0

The 2010 CMU GALE Speech-to-Text System

Download (154.89 kB)
journal contribution
posted on 01.09.2010 by Florian Metze, Roger Hsiao, Qin Jin, Udhyakumar Nallasamy, Tanja Schultz

This paper describes the latest Speech-to-Text system developed for the Global Autonomous Language Exploitation ("GALE") domain by Carnegie Mellon University (CMU). This systems uses discriminative training, bottle-neck features and other techniques that were not used in previous versions of our system, and is trained on 1150 hours of data from a variety of Arabic speech sources. In this paper, we show how different lexica, pre-processing, and system combination techniques can be used to improve the final output, and provide analysis of the improvements achieved by the individual techniques.

History

Publisher Statement

Copyright 2010 ISCA

Date

01/09/2010

Exports

Exports