In this paper, we follow the minimum error principle for acoustic modeling and formulate error objectives in insertion, deletion, and substitution separately for minimization duri...
In this paper, we describe a novel speaker adaptation algorithm based on Gaussian mixture weight adaptation. A small number of latent speaker vectors are estimated with non-negati...
The performance of a multiuser MIMO broadcast system depends highly on how the users being served are selected from the pool of users requesting service. Though dirty paper coding...
This paper describes recent advances at LIMSI in Mandarin Chinese speech-to-text transcription. A number of novel approaches were introduced in the different system components. Th...
Lori Lamel, Jean-Luc Gauvain, Viet-Bac Le, Ilya Op...
In this paper, we propose a novel feature space adaptation technique to improve the robustness of speech recognition in noisy environments. Histogram equalization (HEQ) is an effe...