This paper focuses on a solution to better adapt ASR systems, whose language models (LM) are usually trained on topic-independent corpora, to new topics, in particular in the case...
Abstract. A novel approach for model set based object segmentation is described. The proposed method enables the using of a model set to guide the object segmentation. The object s...
The problem of automatic text segmentation is subcategorized into two different problems: thematic segmentation into rather large topically selfcontained sections and splitting int...
This paper studies the influence of n-gram language models in the recognition of sung phonemes and words. We train uni-, bi-, and trigram language models for phonemes and bi- and...
A common approach to extract phonemes of sign language is to use an unsupervised clustering algorithm to group the sign segments. However, simple clustering algorithms based on dis...