Abstract. Trademark image retrieval is becoming an important application for logo registry, veri cation, and design. There are two major problems about the current approaches to tr...
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...
Hidden Markov models have become the preferred technique for visual recognition of human gestures. However, the recognition rate depends on the set of visual features used, and al...
The performance of automatic speech recognition (ASR) systems in the presence of noise is an area that has attracted a lot of research interest. Additive noise from interfering no...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...