This paper presents a new domain compensation framework by using phonetically discriminative features which are extracted from domain-dependent deep neural networks (DNNs). The domain compensation can be applied in both unsupervised and supervised manner, depending on whether the domain information of the development data is provided or not in advance. In supervised manner, the DNNs are trained on...

作者： Ivan Lopez-Arevalo , Victor J Sosa-Sosa , Franco Rojas-Lopez , Edgar Tello-Leal