Woosung Kim 
Dept. of Computer Science/Center for Language & Speech Processing
The Johns Hopkins University

Title:
Language Model Adaptation for Automatic Speech Recognition 
and Statistical Machine Translation
ABSTRACT

Language modeling is crucial in many natural language applications
such as automatic speech recognition and machine translation.  Due to
the complexity of natural language grammars, statistical techniques
have been dominant for language modeling.  All statistical modeling
techniques, in principle, work under some conditions: 1) a reasonable
amount of training data is available and 2) the training data comes
from the same or similar population as the test data to which we
eventually want to apply our model.  This talk presents new methods
to handle the problem when those conditions are not met in statistical
language modeling---language model adaptations.

In order to tackle the data scarcity problem in resource-deficient
languages, we propose methods to take advantage of a resource-rich
language such as English, utilizing cross-lingual information
retrieval followed by machine translation.  We next experiment the
language model adaptation technique in a different language, English
which is resource-rich and in a different application, the
statistical machine translation task.  Experimental results show that
our adaptation techniques are effective for statistical machine
translation as well as speech recognition.

BIO

Woosung Kim is expected to receive his Ph.D. degree from the Computer
Science dept. at the Johns Hopkins University in 2004. He is also
affiliated with the Center for Language and Speech Processing working
on language modeling, speech recognition, and machine translation.
He did a summer intern in SpeechWorks (now ScanSoft) and prior to
joining Hopkins, he worked with Korea Telecom as a researcher.