We propose to improve speech recognition performance on speaker-independent, mixed language speech by asymmetric acoustic modeling. Mixed language is either inter-sentential code ...
In the presence of environmental noise, speakers tend to adjust their speech production in an effort to preserve intelligible communication. The noise-induced speech adjustments, c...
This paper presents an improved wavelet-based dereverberation method for automatic speech recognition (ASR). Dereverberation is based on filtering reverberant wavelet coefficients...
Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features ext...
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...