In this study, we propose a simple yet effective method for incorporating the source speaker's characteristics in the target speaker's speech. This allows our model to generate the speech of the target speaker with the style of the source speaker. To achieve this, we focus on the attention model within the speech synthesis model, which learns various speaker features such as spectrogram, pitch, intensity, formant, pulse, and voice breaks.
View Article and Find Full Text PDFThe effect of wettability on the migration of dense non-aqueous phase liquids (DNAPLs) through a rough-walled fracture was investigated. The migration characteristics of DNAPL were found to be strongly dependent on the wettability. For a fracture with a hydrophilic surface, DNAPL migrated through larger apertures as disconnected blobs when the groundwater flow regime was linear (Re=1).
View Article and Find Full Text PDF