Abstract: The Learning Management Systems present learning
environment which offers a collection of e-learning tools in a
package that allows a common interface and information sharing
among the tools. South East European University initial experience
in LMS was with the usage of the commercial LMS-ANGEL. After a
three year experience on ANGEL usage because of expenses that
were very high it was decided to develop our own software. As part
of the research project team for the in-house design and development
of the new LMS, we primarily had to select the features that would
cover our needs and also comply with the actual trends in the area of
software development, and then design and develop the system. In
this paper we present the process of LMS in-house development for
South East European University, its architecture, conception and
strengths with a special accent on the process of migration and
integration with other enterprise applications.
Abstract: The current speech interfaces in many military
applications may be adequate for native speakers. However,
the recognition rate drops quite a lot for non-native speakers
(people with foreign accents). This is mainly because the nonnative
speakers have large temporal and intra-phoneme
variations when they pronounce the same words. This
problem is also complicated by the presence of large
environmental noise such as tank noise, helicopter noise, etc.
In this paper, we proposed a novel continuous acoustic feature
adaptation algorithm for on-line accent and environmental
adaptation. Implemented by incremental singular value
decomposition (SVD), the algorithm captures local acoustic
variation and runs in real-time. This feature-based adaptation
method is then integrated with conventional model-based
maximum likelihood linear regression (MLLR) algorithm.
Extensive experiments have been performed on the NATO
non-native speech corpus with baseline acoustic model trained
on native American English. The proposed feature-based
adaptation algorithm improved the average recognition
accuracy by 15%, while the MLLR model based adaptation
achieved 11% improvement. The corresponding word error
rate (WER) reduction was 25.8% and 2.73%, as compared to
that without adaptation. The combined adaptation achieved
overall recognition accuracy improvement of 29.5%, and
WER reduction of 31.8%, as compared to that without
adaptation.