Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
A binaural algorithm to simultaneously detect the azimuth angle and the pitch of the sound source is proposed in this paper. This algorithm is extended from the stereausis model w...
This paper presents a new keypoint-based approach to nearduplicate images detection. It consists of three steps. Firstly, the keypoints of images are extracted and then matched. S...
Single sensor digital cameras capture one color value for every pixel location. The remaining two color channel values need to be estimated to obtain a complete color image. This ...
In this paper, a robust feature for text-independent speaker recognition is proposed, which simulate the response mode of cochlear neurons in processing acoustic signal. The featu...