Various techniques have previously been proposed for the separation of convolutive mixtures. These techniques can be classified as stochastic, adaptive, and deterministic. Stochast...
This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...
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...
Abstract--In this paper, a new model-based algorithm for optimizing the MPEG-Advanced Audio Coder (AAC) in MS-stereo mode is presented. This algorithm is an extension to stereo sig...
Given a large audio database of music recordings, the goal of classical audio identification is to identify a particular audio recording by means of a short audio fragment. Even th...