In this paper we propose a novel order-recursive training algorithm for kernel-based discriminants which is computationally efficient. We integrate this method in a hybrid HMM-bas...
Interpreting fully natural speech is an important goal for spoken language understanding systems. However, while corpus studies have shown that about 10% of spontaneous utterances...
This paper presents a unified probabilistic framework for denoising and dereverberation of speech signals. The framework transforms the denoising and dereverberation problems into...
The MiPPS library supports a hybrid model of parallel programming. The library is targeted at commodity multiprocessors, with support for clusters. The implementation of the concu...
Current speech synthesis technology is difficult to understand in everyday noise situations. Although there is a significant body of work on how humans modify their speech in nois...