file.pdf (154.89 kB)
Download file

The 2010 CMU GALE Speech-to-Text System

Download (154.89 kB)
journal contribution
posted on 01.09.2010, 00:00 by Florian MetzeFlorian 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.


Publisher Statement

Copyright 2010 ISCA