We attemped to improve recognition accuracy by reducing the inadequacies of the lexicon and language model. Specifically we address the following three problems: (1) the best size...
Richard M. Schwartz, Long Nguyen, Francis Kubala, ...
Given a specific information need, documents of the wrong genre can be considered as noise. From this perspective, genre classification helps to separate relevant documents from...
Andrea Stubbe, Christoph Ringlstetter, Klaus U. Sc...
In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoust...
Splitting a speech signal into speakers is the main goal of a speaker diarization system, which has become an important building block in many speech processing algorithms. Curren...
In multiple hypotheses testing, it is important to control the probability of rejecting "true" null hypotheses. A standard procedure has been to control the family-wise ...